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

    Neuronpedia

    INDEX
    Explanations

    a specific marker for the beginning of a new section or context in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ктан
    -0.53
    ↵
    -0.51
    </strong>
    -0.51
     мәкал
    -0.51
     NUKAT
    -0.49
    djangoproject
    -0.49
    ніципа
    -0.45
     nakalista
    -0.45
    Prosec
    -0.44
    šķ
    -0.44
    POSITIVE LOGITS
     transfieras
    0.72
     épis
    0.71
    MLLoader
    0.69
    ThroughAttribute
    0.68
     provisoire
    0.67
     consultato
    0.63
    struzioni
    0.60
     ſeveral
    0.60
     expériment
    0.60
     ſome
    0.59
    Act Density 0.038%

    No Known Activations