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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horner
    -0.68
    críbete
    -0.63
     Justus
    -0.62
     eriş
    -0.60
    airy
    -0.60
    duplex
    -0.59
     clique
    -0.59
    ahuila
    -0.59
    務省
    -0.58
    xAxis
    -0.58
    POSITIVE LOGITS
    Taking
    1.28
    take
    1.26
     taken
    1.23
     Taking
    1.20
     take
    1.18
    took
    1.16
    Take
    1.16
    taken
    1.16
     taking
    1.15
    taking
    1.14
    Act Density 0.081%

    No Known Activations