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

    Neuronpedia

    INDEX
    Explanations

    mentions of promises or assurances of future actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating participation or interaction with activities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.78
    tained
    -0.67
     hindsight
    -0.65
    ²¾
    -0.63
    aq
    -0.58
    hess
    -0.56
    paren
    -0.56
    ð
    -0.55
    fram
    -0.55
     dated
    -0.54
    POSITIVE LOGITS
     will
    1.98
    will
    1.77
     WILL
    1.70
    'll
    1.59
    Will
    1.57
     Will
    1.45
     SHALL
    1.41
     won
    1.26
     wont
    1.25
     shall
    1.24
    Act Density 0.411%

    No Known Activations