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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations, surprises, or common occurrences related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypress
    -0.16
    iaux
    -0.15
    vern
    -0.15
     Arts
    -0.14
    rts
    -0.14
    ssel
    -0.14
    riel
    -0.14
    mue
    -0.14
    rah
    -0.14
    京
    -0.13
    POSITIVE LOGITS
    alli
    0.18
     Sho
    0.15
    eer
    0.15
     Bauer
    0.15
    .ud
    0.14
     sho
    0.14
    à¹īà¸ĩ
    0.14
    å²Ĺ
    0.14
    .Constraint
    0.14
    ISR
    0.13
    Act Density 0.058%

    No Known Activations