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

    Neuronpedia

    INDEX
    Explanations

    acronyms and technical terms in scientific or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.57
    SourceChecksum
    -0.55
     Mérimée
    -0.50
     gra
    -0.48
    ushman
    -0.47
     pa
    -0.47
     ja
    -0.46
    zkopf
    -0.46
    COUVER
    -0.46
     Op
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.99
     myſelf
    0.98
     Majefty
    0.95
     purpoſe
    0.95
     himſelf
    0.86
     Monfieur
    0.86
     poffible
    0.85
     itſelf
    0.85
     Conſ
    0.84
     themſelves
    0.83
    Act Density 0.300%

    No Known Activations