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

    Neuronpedia

    INDEX
    Explanations

    references to economic and social disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ETA
    -0.15
    aha
    -0.15
    argas
    -0.15
     Wolff
    -0.14
    vale
    -0.14
    lint
    -0.13
    onto
    -0.13
    à¸²à¸ł
    -0.13
    YP
    -0.13
    aniu
    -0.13
    POSITIVE LOGITS
    -gap
    0.19
    ting
    0.16
    gap
    0.16
    579
    0.16
    _ASSUME
    0.15
    /loose
    0.15
     междÑĥ
    0.14
     gap
    0.14
    Orm
    0.14
    ocular
    0.14
    Act Density 0.032%

    No Known Activations