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

    Neuronpedia

    INDEX
    Explanations

    questions and exclamations ending in a question mark

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aku
    -0.77
     background
    -0.73
    apter
    -0.72
    ishable
    -0.69
     encount
    -0.68
    enture
    -0.66
    neau
    -0.65
    alist
    -0.65
    ality
    -0.65
     canoe
    -0.64
    POSITIVE LOGITS
     Surely
    1.06
     Anyway
    0.97
     Well
    0.95
     Why
    0.95
    ?:
    0.95
     Where
    0.94
     Isn
    0.94
     Probably
    0.94
    ?!
    0.93
     Somebody
    0.91
    Act Density 0.092%

    No Known Activations