Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of possessive pronouns or possessive constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation or uncommon symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical or scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite

    The marked tokens represent contractions where an apostrophe is elided or appears in contexts where it marks the abbreviated form of "not" or possessive pronouns (e.g., "hadn't," "didn't," "I'm," "shouldn't," "wasn't"). These represent standard English contraction patterns in narrative and conversational text.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @kparkhamchuk
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.70
     Signalez
    -0.61
    baomidou
    -0.53
    dymyr
    -0.49
    quel
    -0.49
    RequiresApi
    -0.49
     onOptions
    -0.48
    contentLoaded
    -0.48
     WebDriverWait
    -0.48
    alibaba
    -0.47
    POSITIVE LOGITS
     Diſ
    0.67
     ſon
    0.60
     Conſ
    0.59
     Daß
    0.58
     reaſon
    0.58
     Reſ
    0.57
     moſt
    0.56
     diſt
    0.56
    —“
    0.55
    ”—
    0.55
    Act Density 0.157%

    No Known Activations