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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement in and out of a place

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    etheless
    -0.82
    hematically
    -0.67
    acci
    -0.65
    erick
    -0.63
    swick
    -0.63
    ä½ľ
    -0.63
    ilon
    -0.61
    owell
    -0.61
    hammad
    -0.59
    iola
    -0.59
    POSITIVE LOGITS
     forth
    1.08
     ruin
    0.78
    rounder
    0.78
     spoil
    0.73
     fro
    0.71
    Ô
    0.69
     greet
    0.68
     join
    0.68
    uin
    0.67
     destroy
    0.66
    Act Density 0.067%

    No Known Activations