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

    Neuronpedia

    INDEX
    Explanations

    words related to discrimination, criticism, and social movements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ilogy
    -0.73
    mma
    -0.69
    ften
    -0.68
    ariat
    -0.67
    undrum
    -0.66
    agame
    -0.64
     THERE
    -0.64
    inator
    -0.64
    iphate
    -0.63
    ocene
    -0.63
    POSITIVE LOGITS
     situations
    0.86
     amounts
    0.85
     occasions
    0.82
     quantities
    0.79
     proportions
    0.78
     levels
    0.77
     objects
    0.76
     threats
    0.76
     periods
    0.75
     parts
    0.75
    Act Density 12.822%

    No Known Activations