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

    Neuronpedia

    INDEX
    Explanations

    sentences containing phrases emphasizing a specific degree or aspect

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Izan
    -0.70
     Anaheim
    -0.69
    skirts
    -0.64
    letters
    -0.63
     memos
    -0.63
     Elections
    -0.61
     Ort
    -0.60
     instructions
    -0.60
    outs
    -0.60
    Exception
    -0.59
    POSITIVE LOGITS
     cohesive
    1.15
     coherent
    1.12
     meaningful
    1.12
     reasonable
    1.11
    rouse
    1.07
     lot
    1.06
     decent
    1.04
     realistic
    1.01
     positive
    1.00
     tangible
    0.98
    Act Density 0.395%

    No Known Activations