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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ..."
    -0.65
    ;}
    -0.63
    #$
    -0.56
    Magikarp
    -0.55
    venge
    -0.54
    eded
    -0.53
    ********
    -0.52
     dressing
    -0.52
     sleeping
    -0.51
    chest
    -0.51
    POSITIVE LOGITS
    endum
    0.70
    othy
    0.64
    ificantly
    0.63
    raltar
    0.63
    surprisingly
    0.61
    miah
    0.61
     Conclusion
    0.61
    prisingly
    0.60
    yssey
    0.60
    ibliography
    0.59
    Act Density 0.412%

    No Known Activations