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

    Neuronpedia

    INDEX
    Explanations

    equality and negation in mathematical expressions or logical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancel
    -0.17
     pac
    -0.16
    PTR
    -0.16
     neutral
    -0.16
    CHED
    -0.15
    ância
    -0.15
    496
    -0.15
     Neutral
    -0.14
     programm
    -0.14
    urnished
    -0.14
    POSITIVE LOGITS
    inker
    0.16
    gii
    0.15
    ilon
    0.15
    ipt
    0.14
    IOUS
    0.14
    iron
    0.14
    iks
    0.13
    ari
    0.13
    606
    0.13
    Fuse
    0.13
    Act Density 0.003%

    No Known Activations