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

    Neuronpedia

    INDEX
    Explanations

    indications of storytelling and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.62
     defaultstate
    -0.55
     Chwiliwch
    -0.54
    antaranya
    -0.52
    :✨
    -0.50
     antaranya
    -0.48
     HFILL
    -0.48
    EDEFAULT
    -0.48
    roek
    -0.47
    IntoConstraints
    -0.46
    POSITIVE LOGITS
    こういう
    0.81
     nowadays
    0.63
     бывает
    0.62
    こういった
    0.62
     politicians
    0.62
     democracies
    0.62
     cults
    0.58
     monopolies
    0.57
     fandoms
    0.56
     dictators
    0.55
    Act Density 0.980%

    No Known Activations