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

    Neuronpedia

    INDEX
    Explanations

    words related to delusion or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISON
    -0.19
    yny
    -0.18
    ç§
    -0.17
    wheel
    -0.15
    zzo
    -0.15
    yn
    -0.15
     viên
    -0.15
    ably
    -0.14
    lou
    -0.14
    ellite
    -0.14
    POSITIVE LOGITS
     del
    0.27
    uge
    0.23
    (del
    0.23
    oit
    0.22
    ivered
    0.22
    aware
    0.21
    .del
    0.21
     Del
    0.21
    phin
    0.21
    iber
    0.21
    Act Density 0.019%

    No Known Activations