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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and entities, particularly in political and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     expl
    -0.76
     DRA
    -0.69
     Toc
    -0.65
     Turki
    -0.65
    ingly
    -0.64
     Whitley
    -0.63
     goi
    -0.63
     asl
    -0.63
     Tint
    -0.61
     Stripes
    -0.60
    POSITIVE LOGITS
    konomi
    0.94
     Sagan
    0.93
     igång
    0.84
    πάρχ
    0.82
     Samuels
    0.80
     بيها
    0.80
    enterOuterAlt
    0.79
     lotes
    0.79
     Avila
    0.79
    writeField
    0.78
    Act Density 3.454%

    No Known Activations