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

    Neuronpedia

    INDEX
    Explanations

    instances of negative feedback or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.09
    acific
    -0.07
    endon
    -0.07
    ISMATCH
    -0.07
    æł·çļĦ
    -0.07
     é¦Ļ
    -0.07
    سÙħØ©
    -0.07
    iente
    -0.07
    rer
    -0.07
    onn
    -0.07
    POSITIVE LOGITS
    /null
    0.09
    -negative
    0.08
    _INFINITY
    0.08
    /n
    0.07
    rones
    0.07
    IntegerField
    0.07
    -positive
    0.06
    ities
    0.06
    /problem
    0.06
    _integer
    0.06
    Act Density 0.012%

    No Known Activations