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

    Neuronpedia

    INDEX
    Explanations

    references to racial dynamics and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĴ
    -0.16
    ENCH
    -0.16
     Interfaces
    -0.14
    amarin
    -0.14
     actionTypes
    -0.14
    ACES
    -0.14
    commons
    -0.14
    itest
    -0.14
    _Tis
    -0.14
    uples
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.15
     recip
    0.15
    iro
    0.15
    .bb
    0.15
    ffe
    0.14
     reciprocal
    0.14
    Č↵
    0.14
    chg
    0.14
     Invitation
    0.14
     reverse
    0.14
    Act Density 0.168%

    No Known Activations