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

    Neuronpedia

    INDEX
    Explanations

    sentence endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instinct
    -0.79
     glim
    -0.78
     dracon
    -0.76
     tremend
    -0.75
     dove
    -0.73
     glyph
    -0.73
    azo
    -0.72
     butterfly
    -0.72
     elbow
    -0.71
     comet
    -0.70
    POSITIVE LOGITS
    India
    1.34
    Apart
    1.34
    Sources
    1.34
    Besides
    1.33
    Interestingly
    1.32
     Besides
    1.32
    Talking
    1.30
    However
    1.28
    Moreover
    1.27
    According
    1.26
    Act Density 0.257%

    No Known Activations