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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mens
    -0.19
    onders
    -0.17
    itage
    -0.16
    uset
    -0.15
    unger
    -0.15
    ÃĥO
    -0.14
    loit
    -0.14
    abler
    -0.14
    ENSION
    -0.14
    mos
    -0.14
    POSITIVE LOGITS
    -of
    0.21
    da
    0.18
    ove
    0.18
    Uvs
    0.15
    ve
    0.15
    ’ve
    0.15
     addCriterion
    0.15
    've
    0.14
    ÛĮÙģ
    0.14
    ovu
    0.14
    Act Density 0.014%

    No Known Activations