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

    Neuronpedia

    INDEX
    Explanations

    phone numbers and contact information

    oai_token-act-pair · gpt-3.5-turbo

    telephone numbers and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stacking
    -0.76
    raints
    -0.74
    igree
    -0.73
    Äĩ
    -0.71
     Conclusion
    -0.68
    phabet
    -0.68
     pie
    -0.68
     inval
    -0.65
    cock
    -0.64
    sort
    -0.64
    POSITIVE LOGITS
    GH
    0.86
     toll
    0.82
    Alert
    0.79
     Toll
    0.79
    Fax
    0.76
    76561
    0.73
     Amph
    0.71
    tips
    0.70
    fax
    0.70
     nm
    0.69
    Act Density 0.079%

    No Known Activations