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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal concerns and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fifty
    -0.17
     lagi
    -0.16
    49
    -0.15
    orget
    -0.15
    61
    -0.14
     true
    -0.14
    611
    -0.14
     truly
    -0.14
     earlier
    -0.14
    uit
    -0.14
    POSITIVE LOGITS
    aeda
    0.15
    ExecutionContext
    0.14
    pawn
    0.14
    .named
    0.14
    PCP
    0.14
     ấm
    0.14
    illis
    0.14
    人æ°Ĺ
    0.14
    ediator
    0.13
    Naming
    0.13
    Act Density 0.518%

    No Known Activations