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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and terms related to statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -1.03
    ↵↵
    -1.01
     &
    -0.85
     $
    -0.84
     
    -0.75
     \
    -0.73
     I
    -0.71
    ↵
    -0.68
     end
    -0.67
    '
    -0.64
    POSITIVE LOGITS
     myſelf
    1.54
     itſelf
    1.50
     Efq
    1.44
     pleaſure
    1.42
    ſelf
    1.39
     purpoſe
    1.39
     Jefus
    1.35
     houſe
    1.31
     Reſ
    1.29
     Monfieur
    1.29
    Act Density 2.603%

    No Known Activations