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

    Neuronpedia

    INDEX
    Explanations

    terms indicating degrees of correctness or falseness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.34
    ar
    -0.27
    ore
    -0.25
    eru
    -0.22
    ORE
    -0.21
    at
    -0.21
    erse
    -0.20
    arro
    -0.20
    erer
    -0.20
    arb
    -0.19
    POSITIVE LOGITS
    hetics
    0.22
    hetic
    0.21
    ev
    0.20
    sal
    0.19
    ead
    0.19
    eb
    0.18
    ing
    0.18
    imate
    0.18
    ee
    0.17
    t
    0.17
    Act Density 0.044%

    No Known Activations