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

    Neuronpedia

    INDEX
    Explanations

    text enclosed in double quotation marks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ²¾
    -0.81
    thur
    -0.68
    ife
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
    acas
    -0.66
    ãĥ¯ãĥ³
    -0.66
    ¬¼
    -0.63
    ernal
    -0.61
    worldly
    -0.60
    anmar
    -0.59
    POSITIVE LOGITS
    /"
    0.95
    [
    0.80
     meaning
    0.73
     referring
    0.73
    {
    0.70
    SPONSORED
    0.69
    ([
    0.66
    advertisement
    0.66
     i
    0.64
     Encyclopedia
    0.62
    Act Density 0.102%

    No Known Activations