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

    Neuronpedia

    INDEX
    Explanations

    expressions related to assertion and belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بÙĪÙĦ
    -0.19
    ossip
    -0.17
    utow
    -0.16
    ostel
    -0.15
     kvin
    -0.15
    VISIBLE
    -0.15
    tryside
    -0.15
     Erotische
    -0.15
    ayıp
    -0.15
    AGMA
    -0.14
    POSITIVE LOGITS
     told
    0.48
     given
    0.42
    given
    0.35
     Given
    0.32
     asked
    0.32
    Given
    0.31
     offered
    0.29
     informed
    0.28
    Asked
    0.27
     presented
    0.27
    Act Density 0.192%

    No Known Activations