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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    une
    -0.17
    unes
    -0.17
    मर
    -0.17
    mes
    -0.16
    retch
    -0.15
    lify
    -0.15
    æ¡£
    -0.14
    mos
    -0.14
    gie
    -0.14
    mund
    -0.14
    POSITIVE LOGITS
    ingly
    0.32
    ably
    0.18
    ively
    0.18
     surprise
    0.17
    /conf
    0.16
    azo
    0.16
    visor
    0.16
    ektor
    0.15
     tactics
    0.15
     factor
    0.15
    Act Density 0.027%

    No Known Activations