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

    Neuronpedia

    INDEX
    Explanations

    percentage values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erness
    -0.15
    exus
    -0.15
    esco
    -0.14
    pcm
    -0.14
    eren
    -0.14
    ares
    -0.13
    ë£Į
    -0.13
     .:
    -0.13
    _prime
    -0.13
    elines
    -0.13
    POSITIVE LOGITS
     pound
    0.18
     hell
    0.17
    Hell
    0.16
     Hell
    0.16
    istrov
    0.16
    zag
    0.16
    dots
    0.14
     alf
    0.14
    hoff
    0.14
     cult
    0.14
    Act Density 0.009%

    No Known Activations