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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulas
    -0.17
    reste
    -0.16
    çľī
    -0.15
     Pent
    -0.15
     pent
    -0.14
    Alignment
    -0.14
    tk
    -0.14
     Britain
    -0.14
     Falk
    -0.14
    ULA
    -0.14
    POSITIVE LOGITS
    acl
    0.16
    edicine
    0.15
    .liferay
    0.15
    /Area
    0.15
    vox
    0.15
    geo
    0.15
    iers
    0.15
    isti
    0.14
     medicine
    0.14
    jian
    0.14
    Act Density 0.030%

    No Known Activations