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

    Neuronpedia

    INDEX
    Explanations

    units of measurement and related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    zac
    -0.65
    EStream
    -0.64
    mble
    -0.64
    yrim
    -0.61
    ilaterally
    -0.60
    ruck
    -0.59
    geon
    -0.58
    anamo
    -0.57
    ividual
    -0.57
    raised
    -0.56
    POSITIVE LOGITS
    perature
    0.72
     soda
    0.64
    adoes
    0.63
    obar
    0.61
     metic
    0.55
     exha
    0.54
    Ü
    0.54
     Drift
    0.53
    iencies
    0.53
    ARDS
    0.53
    Act Density 8.497%

    No Known Activations