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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an excessive amount or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "too" indicating excessiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.74
    estamp
    -0.59
    ODE
    -0.59
    76561
    -0.59
    uzzle
    -0.58
     Pioneer
    -0.57
    craft
    -0.57
    ounces
    -0.57
    hyde
    -0.55
     elig
    -0.54
    POSITIVE LOGITS
     many
    0.95
     often
    0.88
     busy
    0.86
     much
    0.85
     bad
    0.84
    Much
    0.78
    entimes
    0.77
     Many
    0.76
     costly
    0.76
     afraid
    0.75
    Act Density 0.034%

    No Known Activations