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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to opinions and criticism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    byter
    -0.63
    abad
    -0.62
    enegger
    -0.62
    entle
    -0.61
    foreseen
    -0.59
    ELL
    -0.59
    quer
    -0.57
    liam
    -0.56
    ells
    -0.56
    elta
    -0.53
    POSITIVE LOGITS
     of
    1.33
     thereof
    1.14
    Of
    1.04
     Of
    1.02
    of
    1.00
     OF
    0.94
     enough
    0.77
    oft
    0.76
    ta
    0.75
     lest
    0.75
    Act Density 0.179%

    No Known Activations