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

    Neuronpedia

    INDEX
    Explanations

    indicators of statistical data and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.85
     "
    -0.78
     and
    -0.77
     (
    -0.74
     $\
    -0.72
     I
    -0.71
     in
    -0.70
     di
    -0.70
     or
    -0.67
     en
    -0.67
    POSITIVE LOGITS
     itſelf
    1.49
    ſelf
    1.47
     Efq
    1.47
    ſelves
    1.45
     myſelf
    1.44
     purpoſe
    1.36
     Majefty
    1.36
     Jefus
    1.35
     ſeveral
    1.33
     Reſ
    1.31
    Act Density 0.450%

    No Known Activations