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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical details such as file names, formats, and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grounding
    -0.85
     horizont
    -0.76
     rall
    -0.73
     withd
    -0.71
     unstoppable
    -0.71
    urrection
    -0.70
     tidal
    -0.69
     erosion
    -0.68
     homelessness
    -0.66
    vation
    -0.66
    POSITIVE LOGITS
    html
    1.40
    htm
    1.31
    txt
    1.28
    aspx
    1.14
    png
    1.13
    mp
    1.12
    jpg
    1.10
     Retrieved
    1.09
    php
    1.08
    blogspot
    1.08
    Act Density 0.089%

    No Known Activations