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

    Neuronpedia

    INDEX
    Explanations

    instances of reading and references to articles or posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.66
     GIPHY
    -0.63
    ूरत
    -0.62
    elemField
    -0.58
    ьаж
    -0.53
    zzá
    -0.53
    стота
    -0.52
    Filmography
    -0.52
     đổi
    -0.51
     filmed
    -0.51
    POSITIVE LOGITS
     carefully
    0.84
     aloud
    0.73
     descriptions
    0.70
     attentively
    0.67
    caref
    0.65
     referenties
    0.60
     articles
    0.60
     intently
    0.58
    adaptiveStyles
    0.57
     reports
    0.57
    Act Density 0.144%

    No Known Activations