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

    Neuronpedia

    INDEX
    Explanations

    references to legal and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.16
     Gutenberg
    -0.16
    ailer
    -0.15
    arella
    -0.14
    _increment
    -0.14
     tô
    -0.14
     zorun
    -0.14
     buá»Ļc
    -0.14
    anners
    -0.14
    ruits
    -0.14
    POSITIVE LOGITS
     pardon
    0.43
     pard
    0.42
     commute
    0.34
     commuting
    0.32
     comm
    0.32
     release
    0.31
    pard
    0.31
     Clem
    0.30
     parole
    0.28
     Release
    0.28
    Act Density 0.069%

    No Known Activations