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

    Neuronpedia

    INDEX
    Explanations

    references to critical theories and social justice concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vern
    -0.17
    osal
    -0.17
    ï¸
    -0.17
    oire
    -0.15
    opa
    -0.15
    -Mart
    -0.15
    ylland
    -0.15
     Representation
    -0.15
    ırı
    -0.14
    kop
    -0.14
    POSITIVE LOGITS
     apply
    0.26
    apply
    0.25
     applied
    0.24
    .apply
    0.23
     onto
    0.23
     APPLY
    0.23
     Apply
    0.23
    Apply
    0.23
     applies
    0.21
     Applied
    0.20
    Act Density 0.059%

    No Known Activations