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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpected occurrences in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andelier
    -0.16
    aben
    -0.15
    ografia
    -0.15
    urnal
    -0.14
    gratis
    -0.14
     disasters
    -0.14
    ustos
    -0.13
    æļĹ
    -0.13
    /inet
    -0.13
    ().'/
    -0.13
    POSITIVE LOGITS
    ç«Ł
    0.18
    IVA
    0.15
    unction
    0.15
    egree
    0.14
    iva
    0.14
    eldorf
    0.14
    osate
    0.14
    ìĥģ
    0.14
    å±ħ
    0.13
     Estate
    0.13
    Act Density 0.045%

    No Known Activations