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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ept
    -0.17
     Rica
    -0.16
    gue
    -0.16
    ibern
    -0.15
    kou
    -0.15
    onor
    -0.15
    keley
    -0.15
    ey
    -0.15
    beth
    -0.15
    zing
    -0.14
    POSITIVE LOGITS
    acular
    0.18
    iesz
    0.18
    ifice
    0.17
    acles
    0.17
    iol
    0.15
    icht
    0.15
    acy
    0.15
     else
    0.15
    wel
    0.15
    063
    0.14
    Act Density 0.037%

    No Known Activations