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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that indicate moral or ethical violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ons
    -0.16
    ÑģÑĤоÑı
    -0.15
     McN
    -0.15
    atus
    -0.15
    gs
    -0.14
    DataSource
    -0.14
    ³
    -0.14
    pest
    -0.14
    andal
    -0.14
    ough
    -0.14
    POSITIVE LOGITS
    ãģ¥
    0.17
    ekten
    0.17
    çłĶ究æīĢ
    0.15
    .hh
    0.15
    .dtd
    0.15
    .ascii
    0.14
     Haw
    0.14
    .toFloat
    0.14
    ANDLE
    0.13
    lemn
    0.13
    Act Density 0.001%

    No Known Activations