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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "not" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esco
    -0.17
    ause
    -0.15
    addy
    -0.15
    486
    -0.14
    planation
    -0.14
    onas
    -0.14
    atsu
    -0.14
    px
    -0.14
    ']!='
    -0.14
     Crosby
    -0.13
    POSITIVE LOGITS
    ices
    0.16
    iced
    0.16
    withstanding
    0.16
    icias
    0.16
    icing
    0.15
    FFE
    0.15
    ewriter
    0.15
    ched
    0.15
    ³
    0.15
    CHED
    0.15
    Act Density 0.035%

    No Known Activations