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

    Neuronpedia

    INDEX
    Explanations

    quotations or dialogue markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.22
    's
    -0.17
    're
    -0.17
    i
    -0.17
    :
    -0.16
    a
    -0.15
    ,
    -0.15
    aad
    -0.15
    -A
    -0.15
    s
    -0.15
    POSITIVE LOGITS
    ãĢģ“
    0.22
    @nate
    0.18
    /'
    0.18
    tempts
    0.17
    urement
    0.15
    .scalablytyped
    0.14
    OGLE
    0.14
     průbÄĽhu
    0.14
    ï¼ļ"
    0.13
    thur
    0.13
    Act Density 0.200%

    No Known Activations