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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve announcements or declarations, often related to notable events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .EVT
    -0.15
     Han
    -0.14
    mons
    -0.14
     erotiske
    -0.14
    imson
    -0.14
    osph
    -0.14
    боÑĤ
    -0.13
    arkan
    -0.13
    onom
    -0.13
     eventual
    -0.13
    POSITIVE LOGITS
    ingo
    0.14
     Eis
    0.14
    asting
    0.14
    ลาย
    0.14
    lijke
    0.14
    098
    0.13
    Uvs
    0.13
    etta
    0.13
    essel
    0.13
    945
    0.13
    Act Density 0.070%

    No Known Activations