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

    Neuronpedia

    INDEX
    Explanations

    references to examples or illustrations of concepts or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shalt
    -0.64
     raiſ
    -0.56
     OkHttpClient
    -0.55
     coronation
    -0.52
     Scud
    -0.52
     materna
    -0.50
     Koran
    -0.49
     corduroy
    -0.48
     curative
    -0.47
    itanya
    -0.47
    POSITIVE LOGITS
    Vidite
    0.82
     illustrate
    0.81
     illustrates
    0.79
     exemplifies
    0.77
     autorytatywna
    0.77
     exemplify
    0.73
     how
    0.69
     Roskov
    0.68
     illustrating
    0.68
    windowFixed
    0.67
    Act Density 0.239%

    No Known Activations