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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "clear" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "made clear."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isol
    -0.75
    inse
    -0.74
    asus
    -0.74
    umbn
    -0.74
    INT
    -0.72
    ernels
    -0.69
    ingers
    -0.67
    otin
    -0.65
    prime
    -0.65
    oleon
    -0.64
    POSITIVE LOGITS
     distinctions
    0.90
    ances
    0.88
     distinction
    0.84
     outlines
    0.75
    gow
    0.73
    iary
    0.71
    ance
    0.70
     clear
    0.69
     sailing
    0.69
     unlaw
    0.68
    Act Density 0.019%

    No Known Activations