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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to interactions or agreements involving two parties or multiple sides

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    icio
    -0.66
    urg
    -0.66
    mur
    -0.61
     Gru
    -0.60
    asts
    -0.60
    utsu
    -0.59
    usky
    -0.59
    aic
    -0.59
    sylv
    -0.58
    ulators
    -0.58
    POSITIVE LOGITS
     handshake
    0.75
    finding
    0.68
    frame
    0.65
    fare
    0.64
    sided
    0.63
    point
    0.63
    seeing
    0.60
     occupancy
    0.57
    frames
    0.57
    forward
    0.54
    Act Density 6.341%

    No Known Activations