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

    Neuronpedia

    INDEX
    Explanations

    contact information such as email addresses and phone numbers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     subp
    -0.68
    hov
    -0.63
    Fit
    -0.62
    ±
    -0.61
    roo
    -0.59
     sterling
    -0.57
    anmar
    -0.57
     Bots
    -0.56
    come
    -0.56
    iens
    -0.56
    POSITIVE LOGITS
    =-=-=-=-
    0.88
     voic
    0.72
     Caller
    0.72
     spokesman
    0.68
     toll
    0.65
     by
    0.64
     hotline
    0.63
     pione
    0.62
     spokesperson
    0.62
     telephone
    0.62
    Act Density 0.078%

    No Known Activations