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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific characters or locations along with related fictional events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    acity
    -0.74
    REDACTED
    -0.71
    manship
    -0.70
    auri
    -0.67
     GOODMAN
    -0.62
    rity
    -0.62
    layer
    -0.61
    geist
    -0.60
     Covenant
    -0.60
    nikov
    -0.59
    POSITIVE LOGITS
    igslist
    1.20
    ving
    0.96
    pload
    0.90
    pton
    0.89
    fters
    0.88
    bable
    0.82
    ves
    0.81
    fter
    0.81
    ved
    0.76
    isma
    0.74
    Act Density 4.331%

    No Known Activations