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

    Neuronpedia

    INDEX
    Explanations

    terms related to criticism or analysis of stereotypes and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertino
    -0.20
    stack
    -0.16
    avery
    -0.16
    itan
    -0.15
    .AF
    -0.15
    ãĥ¡ãĥ©
    -0.14
    ismet
    -0.14
    γμα
    -0.14
    stress
    -0.14
    itor
    -0.14
    POSITIVE LOGITS
    wart
    0.18
     Ster
    0.18
    viso
    0.17
    ois
    0.16
    Ïĩει
    0.15
    hread
    0.14
    θε
    0.14
     ster
    0.14
    hed
    0.14
    vant
    0.14
    Act Density 0.010%

    No Known Activations