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

    Neuronpedia

    INDEX
    Explanations

    instances of actions related to checking and marking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Apis
    -0.16
    erland
    -0.15
    ucz
    -0.15
    kul
    -0.15
    ervas
    -0.14
    .baidu
    -0.14
    çķ
    -0.14
    ekler
    -0.14
    æ´ĭ
    -0.14
    NAMESPACE
    -0.14
    POSITIVE LOGITS
    Insets
    0.16
    xes
    0.16
     Dagger
    0.16
    rage
    0.15
    én
    0.15
    UME
    0.15
    èn
    0.14
    ittings
    0.14
    ESS
    0.14
    atab
    0.13
    Act Density 0.009%

    No Known Activations