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

    Neuronpedia

    INDEX
    Explanations

    references to temperature and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.35
    ر
    -0.26
    eras
    -0.26
    l
    -0.25
    lip
    -0.23
    ero
    -0.23
    i
    -0.22
    ln
    -0.22
    lim
    -0.22
    era
    -0.21
    POSITIVE LOGITS
    licit
    0.21
    lica
    0.20
    licate
    0.20
    licity
    0.20
    loi
    0.18
    ersion
    0.18
    lications
    0.18
    loit
    0.17
    loid
    0.17
    ansion
    0.17
    Act Density 0.145%

    No Known Activations