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

    Neuronpedia

    INDEX
    Explanations

    terms related to apologies and expressions of regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enci
    -0.18
     -----------------------------------------------------------------------------↵
    -0.17
     Erk
    -0.16
    öh
    -0.15
    ÑĮÑİ
    -0.14
    elier
    -0.14
    amerate
    -0.14
    indow
    -0.14
    uar
    -0.14
    orent
    -0.14
    POSITIVE LOGITS
     ap
    0.23
     Ap
    0.17
    345
    0.15
    ADB
    0.15
    -ap
    0.15
    .Ap
    0.14
    indrome
    0.14
     ап
    0.14
    FETCH
    0.14
    (ap
    0.14
    Act Density 0.093%

    No Known Activations