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

    Neuronpedia

    INDEX
    Explanations

    names, nicknames, titles, and renaming actions in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ramid
    -0.74
    romy
    -0.73
    icult
    -0.70
    ersen
    -0.68
    imeo
    -0.65
    yrus
    -0.65
    otropic
    -0.65
    umat
    -0.64
    ondo
    -0.62
    berra
    -0.62
    POSITIVE LOGITS
    plates
    0.84
    paces
    0.83
     synonymous
    0.81
    plate
    0.80
     naming
    0.79
     bestowed
    0.78
     slogan
    0.71
    ãĥĩ
    0.70
     recognition
    0.70
     aliases
    0.68
    Act Density 10.628%

    No Known Activations