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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific keywords and phrases in a structured document format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.79
    parsedMessage
    -0.67
     وتسجيلات
    -0.65
     Geſ
    -0.65
     surla
    -0.65
    expandindo
    -0.62
     desmotivaciones
    -0.60
     pleaſure
    -0.60
    AndEndTag
    -0.60
     plufieurs
    -0.60
    POSITIVE LOGITS
    .
    0.35
    alu
    0.35
    Sal
    0.34
    part
    0.34
    lib
    0.34
    ENTOS
    0.34
     http
    0.33
    http
    0.33
    atisk
    0.33
    я
    0.32
    Act Density 0.067%

    No Known Activations