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

    Neuronpedia

    INDEX
    Explanations

    messages conveying personal thoughts or opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.73
     Nanto
    -0.68
    ãĥ©ãĥ³
    -0.65
    Thumbnail
    -0.64
    fig
    -0.64
    021
    -0.63
    610
    -0.63
    externalActionCode
    -0.62
    WER
    -0.61
    otiation
    -0.60
    POSITIVE LOGITS
     joking
    0.85
     kidding
    0.71
     invincible
    0.71
    might
    0.69
     kindred
    0.68
    'd
    0.67
     deserved
    0.66
     gonna
    0.65
     might
    0.65
     Bout
    0.63
    Act Density 0.270%

    No Known Activations