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

    Neuronpedia

    INDEX
    Explanations

    references to leadership positions and titles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arch
    -0.15
    rede
    -0.14
    alta
    -0.14
    _deinit
    -0.14
    лаÑĪ
    -0.14
     bah
    -0.14
    zar
    -0.14
    δή
    -0.14
    chine
    -0.14
    íĮħ
    -0.14
    POSITIVE LOGITS
    uzzi
    0.16
     Washer
    0.16
    blick
    0.15
     deferred
    0.15
     Deferred
    0.14
     membership
    0.14
    'gc
    0.14
    бÑĥд
    0.14
    ationally
    0.14
    igram
    0.14
    Act Density 0.057%

    No Known Activations