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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "or" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouser
    -0.15
    raud
    -0.14
    ron
    -0.14
    Cop
    -0.14
    ÑĸÑģ
    -0.14
    atab
    -0.14
    STM
    -0.14
    cop
    -0.14
    throp
    -0.14
    าล
    -0.14
    POSITIVE LOGITS
    zioni
    0.16
    angs
    0.16
    zew
    0.16
    hur
    0.15
    zÄħ
    0.15
    zia
    0.14
    ÑĢо
    0.14
    olina
    0.14
    leading
    0.14
    /memory
    0.14
    Act Density 0.083%

    No Known Activations