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

    Neuronpedia

    INDEX
    Explanations

    terms related to various filtering and construction technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /&
    -0.15
    673
    -0.15
    ottie
    -0.14
    /language
    -0.14
    rats
    -0.14
     Stam
    -0.14
    aji
    -0.14
    /crypto
    -0.14
    hardt
    -0.14
     safeg
    -0.14
    POSITIVE LOGITS
    å¼ı
    0.42
     style
    0.34
    -style
    0.31
     type
    0.31
    -type
    0.29
    ìĭĿ
    0.28
     Style
    0.26
    -based
    0.25
    style
    0.24
    åŀĭ
    0.24
    Act Density 0.282%

    No Known Activations