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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a focus on specific actions or attributes

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

    "a" followed by uncommon words

    np_acts-logits-general · gemini-2.0-flash

    a followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    襪
    -0.49
     troca
    -0.49
    нес
    -0.48
     Able
    -0.48
     No
    -0.47
    kadi
    -0.46
    ให
    -0.45
     Eins
    -0.45
     Kan
    -0.45
    No
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.08
    ViewFeatures
    0.94
    tableFuture
    0.86
     AssemblyCulture
    0.85
    noinspection
    0.82
    Abit
    0.78
     itſelf
    0.76
    OOTDTY
    0.75
    tvguidetime
    0.75
     ContentValues
    0.74
    Act Density 0.134%

    No Known Activations