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

    Neuronpedia

    INDEX
    Explanations

    references to dishonesty and deception in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.16
    phan
    -0.15
     HomeController
    -0.14
    shal
    -0.14
    mise
    -0.14
    _COPY
    -0.14
    ialized
    -0.14
    WEEN
    -0.14
    /import
    -0.13
    VML
    -0.13
    POSITIVE LOGITS
    /false
    0.19
    inth
    0.15
    akens
    0.15
    ushima
    0.14
    fulness
    0.14
    ulen
    0.14
    areth
    0.14
    Ñĵ
    0.14
    aken
    0.14
    iveness
    0.14
    Act Density 0.051%

    No Known Activations