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

    Neuronpedia

    INDEX
    Explanations

    interrogative sentences ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions or interrogative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.69
    bidden
    -0.66
    oing
    -0.65
     weld
    -0.65
     civilisation
    -0.63
    locked
    -0.60
    bole
    -0.59
    opath
    -0.59
    stem
    -0.58
    olor
    -0.58
    POSITIVE LOGITS
     Answer
    1.22
     Were
    1.17
     Would
    1.16
     Where
    1.11
     Obviously
    1.11
     What
    1.09
     Explain
    1.09
     Seems
    1.08
     How
    1.08
     Does
    1.06
    Act Density 0.073%

    No Known Activations