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

    Neuronpedia

    INDEX
    Explanations

    text related to various data and information without a clear thematic pattern

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yip
    -1.00
    pton
    -0.98
    pheus
    -0.93
    pared
    -0.91
    senal
    -0.90
    perty
    -0.89
    chy
    -0.89
    cci
    -0.88
    hood
    -0.84
    hov
    -0.84
    POSITIVE LOGITS
    rophe
    1.31
    efully
    1.14
    rophic
    1.12
    roph
    1.12
    eful
    1.11
    rup
    1.06
    ruct
    1.05
    hest
    1.02
    odon
    1.01
    rop
    1.00
    Act Density 9.355%

    No Known Activations