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

    Neuronpedia

    INDEX
    Explanations

    statements and expressions related to apologies and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mares
    -0.15
    agg
    -0.15
    osit
    -0.14
     __("
    -0.14
    emale
    -0.14
    ligt
    -0.14
    ordes
    -0.14
     Chains
    -0.13
    uran
    -0.13
    SHARE
    -0.13
    POSITIVE LOGITS
    fax
    0.17
    oming
    0.16
    ÙĨدر
    0.14
    cesso
    0.14
     Quit
    0.13
    846
    0.13
    æĿ¾
    0.13
     åĨ
    0.13
     дÑĢÑĥ
    0.13
     Caf
    0.13
    Act Density 0.097%

    No Known Activations