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

    Neuronpedia

    INDEX
    Explanations

    terms related to social classifications and distinctions, especially those with a negative or critical connotation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     another
    -0.16
     Hra
    -0.15
     Hawth
    -0.15
     none
    -0.14
     with
    -0.14
    Æ°Æ¡i
    -0.14
     twice
    -0.14
     as
    -0.14
     respectively
    -0.14
     many
    -0.14
    POSITIVE LOGITS
    chal
    0.20
    -"
    0.19
    ilib
    0.18
    theless
    0.17
    -New
    0.17
    oner
    0.16
    ulas
    0.16
    (er
    0.16
    plib
    0.16
    atur
    0.15
    Act Density 0.142%

    No Known Activations