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

    Neuronpedia

    INDEX
    Explanations

    instances of surprise or realization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckle
    -0.16
    ationship
    -0.15
    ales
    -0.15
    yonel
    -0.15
    anian
    -0.14
    alia
    -0.13
    ->{_
    -0.13
    离
    -0.13
    ipe
    -0.13
    ASC
    -0.13
    POSITIVE LOGITS
     sight
    0.18
    uger
    0.15
    amac
    0.15
    upon
    0.15
    habi
    0.15
     Britann
    0.15
     upon
    0.14
     Upon
    0.14
     fact
    0.14
     suddenly
    0.14
    Act Density 0.092%

    No Known Activations