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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to statistical analysis and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Slf
    -1.01
    k
    -0.97
    p
    -0.96
    b
    -0.95
    i
    -0.93
    m
    -0.89
    t
    -0.88
    y
    -0.88
    j
    -0.86
    S
    -0.86
    POSITIVE LOGITS
     myſelf
    1.90
     themſelves
    1.89
     itſelf
    1.79
     himſelf
    1.77
     ſeveral
    1.68
    BibitemShut
    1.64
     ་་
    1.57
     Monfieur
    1.57
     pleaſure
    1.56
    ſelves
    1.56
    Act Density 8.075%

    No Known Activations