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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    infra
    -0.16
    è£
    -0.15
    ëĸ
    -0.15
     infra
    -0.14
    iode
    -0.14
    appa
    -0.14
     cáºŃn
    -0.14
    439
    -0.13
    heel
    -0.13
    engage
    -0.13
    POSITIVE LOGITS
    roti
    0.18
    agli
    0.17
    roe
    0.16
    691
    0.14
     Acid
    0.14
     acid
    0.14
    ocker
    0.14
    ddie
    0.14
    ifo
    0.14
     whose
    0.13
    Act Density 0.018%

    No Known Activations