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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe identities or roles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.14
    Intersection
    -0.14
    803
    -0.14
    üb
    -0.14
    ühr
    -0.13
    oteca
    -0.13
    .hu
    -0.13
    AttributeName
    -0.13
    ละ
    -0.13
    eca
    -0.13
    POSITIVE LOGITS
     born
    0.17
    gil
    0.16
     Born
    0.15
     himself
    0.15
    awai
    0.15
    unas
    0.14
    adÃŃ
    0.14
     professional
    0.14
    olley
    0.14
    roupon
    0.14
    Act Density 0.070%

    No Known Activations