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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations or descriptors often indicating excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.91
     Thesaurus
    -0.63
     État
    -0.62
    oole
    -0.62
     Bartholo
    -0.61
     kysy
    -0.61
    URIComponent
    -0.61
     väh
    -0.61
    enderror
    -0.61
     Mindanao
    -0.60
    POSITIVE LOGITS
     genius
    0.70
    :])
    0.64
     BaseActivity
    0.64
     brilliant
    0.61
     geniuses
    0.61
    genius
    0.60
     LiveData
    0.60
    Brilliant
    0.59
     Genius
    0.59
     dresses
    0.58
    Act Density 0.054%

    No Known Activations