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

    Neuronpedia

    INDEX
    Explanations

    key concepts and relationships involving personal identity and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Either
    -0.25
     either
    -0.25
    Either
    -0.24
    either
    -0.22
     EITHER
    -0.20
    éĶĭ
    -0.17
    PFN
    -0.16
    isoft
    -0.15
    íĮĮ
    -0.15
    alendar
    -0.15
    POSITIVE LOGITS
     nor
    0.81
    nor
    0.59
     Nor
    0.56
     NOR
    0.54
    Nor
    0.49
     ni
    0.38
     noch
    0.33
     nors
    0.33
     ||
    0.31
     neither
    0.29
    Act Density 0.017%

    No Known Activations