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

    Neuronpedia

    INDEX
    Explanations

    references to familiarity or knowledge about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.88
    MLLoader
    -0.84
    ItemBackground
    -0.81
     autorytatywna
    -0.81
     onAnimation
    -0.79
    AllAfrica
    -0.78
    bewerken
    -0.77
    brainly
    -0.76
     referenties
    -0.76
     الرياضيه
    -0.76
    POSITIVE LOGITS
    ご存知
    0.56
     notoriously
    0.51
     notori
    0.50
     notorious
    0.48
     or
    0.47
     know
    0.47
     conosci
    0.46
     zná
    0.46
    面目
    0.45
     infamous
    0.45
    Act Density 0.180%

    No Known Activations