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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or ambiguity regarding events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ARTICLE
    -0.68
    ski
    -0.66
     Juda
    -0.66
     reciproc
    -0.61
     conn
    -0.57
    Js
    -0.56
    owship
    -0.56
    Myth
    -0.56
    trip
    -0.55
    ーク
    -0.55
    POSITIVE LOGITS
     details
    1.09
     specifics
    1.06
     unclear
    0.97
    details
    0.91
     particulars
    0.85
     detail
    0.79
     unknown
    0.79
     TBD
    0.76
     unaccount
    0.76
    ��
    0.76
    Act Density 1.206%

    No Known Activations