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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" in varying contexts, possibly indicating comparisons or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maz
    -0.18
    hack
    -0.15
    ande
    -0.15
    Than
    -0.15
    ër
    -0.15
    θεν
    -0.15
    exels
    -0.14
    iversal
    -0.14
    geist
    -0.14
    uido
    -0.14
    POSITIVE LOGITS
    akin
    0.16
    709
    0.16
    abb
    0.14
    707
    0.14
    209
    0.14
    ANGO
    0.14
    SCR
    0.14
    ABB
    0.14
    aby
    0.14
    mer
    0.14
    Act Density 0.143%

    No Known Activations