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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating a lower rank or status

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gerald
    -0.68
    Downloadha
    -0.64
    velt
    -0.63
    bleacher
    -0.62
    kers
    -0.62
    =(
    -0.61
    vez
    -0.60
    ä½ľ
    -0.60
    issan
    -0.59
    Reward
    -0.59
    POSITIVE LOGITS
    hand
    1.29
    arily
    1.19
     baseman
    1.12
    aries
    1.05
    ary
    0.88
     guessing
    0.84
     cousins
    0.78
     glance
    0.78
     cousin
    0.76
     halves
    0.74
    Act Density 0.053%

    No Known Activations