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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.82
     oun
    -0.82
     cod
    -0.80
     unloaded
    -0.72
     liquid
    -0.71
    anus
    -0.69
     homebrew
    -0.69
    anka
    -0.68
     inver
    -0.68
     modular
    -0.67
    POSITIVE LOGITS
     Please
    1.04
    php
    1.01
    push
    0.94
    aspx
    0.93
     However
    0.93
    google
    0.91
    html
    0.90
     Though
    0.89
     Thanks
    0.87
     If
    0.86
    Act Density 0.144%

    No Known Activations