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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rape
    -0.18
    eters
    -0.17
    arkan
    -0.17
    thew
    -0.16
    ishly
    -0.16
    landa
    -0.16
    theless
    -0.15
    sis
    -0.15
    rep
    -0.15
    raq
    -0.15
    POSITIVE LOGITS
    bos
    0.36
    HOLDER
    0.27
    OfBirth
    0.21
    able
    0.21
    holders
    0.21
    ful
    0.21
    lessness
    0.21
     holder
    0.21
    -holder
    0.21
    /time
    0.20
    Act Density 0.087%

    No Known Activations