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

    Neuronpedia

    INDEX
    Explanations

    the term "conduct."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤÑĮ
    -1.67
    ?_
    -1.49
    hin
    -1.44
    romycin
    -1.43
    ––––––––
    -1.40
    ="">
    -1.38
    YPE
    -1.37
    GREEK
    -1.37
     }{
    -1.34
    inner
    -1.34
    POSITIVE LOGITS
    stable
    1.83
    µ
    1.81
    stab
    1.80
    quest
    1.80
    Ī
    1.80
    ifer
    1.80
    igan
    1.77
    versation
    1.72
    vergence
    1.61
    cert
    1.59
    Act Density 0.786%

    No Known Activations