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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or anticipation of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or pending outcomes regarding events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defic
    -0.69
    esville
    -0.60
    enos
    -0.58
    enda
    -0.58
     debtor
    -0.57
     pauses
    -0.56
     pref
    -0.54
    Downloadha
    -0.53
     Meridian
    -0.53
     miscarriage
    -0.53
    POSITIVE LOGITS
    verified
    0.78
    proven
    0.76
    bara
    0.68
     conjecture
    0.68
     determine
    0.66
    lege
    0.65
    ileaks
    0.64
     ascertain
    0.64
     seen
    0.63
     decide
    0.63
    Act Density 0.057%

    No Known Activations