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

    Neuronpedia

    INDEX
    Explanations

    terms related to explicit content and censorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovich
    -0.16
    odyn
    -0.16
     baiser
    -0.14
     Laurel
    -0.14
    oren
    -0.14
    ivr
    -0.14
     Rape
    -0.14
     rapes
    -0.14
    ErrorException
    -0.14
     Rap
    -0.13
    POSITIVE LOGITS
     Moral
    0.16
    ETS
    0.15
    ROUGH
    0.14
    afd
    0.14
    emek
    0.14
    iggins
    0.14
    Ñĵ
    0.14
    FOUND
    0.14
    abet
    0.14
    agraph
    0.14
    Act Density 0.195%

    No Known Activations