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

    Neuronpedia

    INDEX
    Explanations

    titles of stories or works in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Numerade
    -0.47
    drawiam
    -0.47
     nahilalakip
    -0.46
    IntoConstraints
    -0.46
    роятно
    -0.45
     ddelweddau
    -0.43
    RTHOOK
    -0.42
    mtliche
    -0.42
    Hilarious
    -0.41
    :✨
    -0.41
    POSITIVE LOGITS
    TimeTo
    0.52
     Beyond
    0.50
     Into
    0.50
     Where
    0.50
     beyond
    0.49
     Let
    0.49
    iexcl
    0.49
     Welcome
    0.48
     Getting
    0.48
     chasing
    0.48
    Act Density 0.275%

    No Known Activations