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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ɠ
    -0.63
    chequer
    -0.62
     Horst
    -0.60
     Kaufman
    -0.60
    儕
    -0.59
     Montal
    -0.59
    bytes
    -0.59
     елның
    -0.59
    ecake
    -0.59
    queryString
    -0.59
    POSITIVE LOGITS
     Decide
    2.12
     decide
    2.05
     decides
    2.04
    Decide
    2.04
     decided
    2.03
     Decided
    1.92
    decide
    1.87
     deciding
    1.82
    decided
    1.81
     décidé
    1.61
    Act Density 0.089%

    No Known Activations