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

    Neuronpedia

    INDEX
    Explanations

    terms related to decision-making and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.68
    FIG
    -0.65
     anyways
    -0.64
     independ
    -0.63
    iably
    -0.62
    heit
    -0.61
    BA
    -0.61
    dor
    -0.60
    TABLE
    -0.59
    sv
    -0.59
    POSITIVE LOGITS
    antic
    0.70
    aux
    0.69
    bris
    0.68
    leton
    0.66
    care
    0.64
    ele
    0.64
     credits
    0.64
    gone
    0.64
    rations
    0.63
    uter
    0.63
    Act Density 0.929%

    No Known Activations