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

    Neuronpedia

    INDEX
    Explanations

    programming commands and statements

    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
     affili
    -0.87
     patron
    -0.85
     induct
    -0.82
     literacy
    -0.78
     reception
    -0.76
     grounding
    -0.76
     standing
    -0.75
     corrective
    -0.74
     buying
    -0.74
     contributing
    -0.73
    POSITIVE LOGITS
    txt
    1.87
    exe
    1.80
    lua
    1.65
    rb
    1.64
    dll
    1.63
    py
    1.63
    cfg
    1.62
    xml
    1.61
    png
    1.60
    cpp
    1.57
    Act Density 0.074%

    No Known Activations