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

    Neuronpedia

    INDEX
    Explanations

    complex grammatical structures and rhetorical questions, often reflecting disagreement or uncertainty

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

    Follows conversational words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    question mark then okay or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...");
    -0.65
    ثة
    -0.63
    ...";
    -0.59
    ...')
    -0.58
    UserScript
    -0.58
    tagHelperRunner
    -0.57
    PMailer
    -0.57
    انيف
    -0.57
    WHILE
    -0.56
    SharedDtor
    -0.55
    POSITIVE LOGITS
     Okay
    1.34
     Yeah
    1.31
     okay
    1.19
    Yeah
    1.15
     Alright
    1.15
    Okay
    1.15
     yeah
    1.06
     Oh
    1.02
     OK
    1.02
    Alright
    1.01
    Act Density 0.125%

    No Known Activations