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

    Neuronpedia

    INDEX
    Explanations

    references to factors, particularly in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.05
     ſeveral
    -1.01
     purpoſe
    -1.01
     ſever
    -1.00
     Monfieur
    -0.99
     myſelf
    -0.99
     ſind
    -0.99
     raiſ
    -0.99
     ―――――
    -0.97
     pleaſure
    -0.96
    POSITIVE LOGITS
     F
    2.12
     f
    1.91
    F
    1.85
    f
    1.60
     ف
    1.45
     פ
    1.25
     Ф
    1.19
     ф
    1.19
     फ
    1.17
    ف
    1.15
    Act Density 0.343%

    No Known Activations