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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality and conditions in relation to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (s
    -0.17
     Gor
    -0.16
    mage
    -0.14
    ett
    -0.14
    uco
    -0.14
    ádu
    -0.14
     Bad
    -0.14
    rada
    -0.13
    arme
    -0.13
    ience
    -0.13
    POSITIVE LOGITS
    yclopedia
    0.17
     Lans
    0.17
     addCriterion
    0.15
    ajar
    0.15
    arcy
    0.15
    ãĥ³ãĤ¸
    0.14
    jem
    0.14
    inou
    0.14
    лÑİб
    0.14
    ponge
    0.14
    Act Density 0.341%

    No Known Activations