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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and their placements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     here
    -0.52
     ve
    -0.50
    ,
    -0.50
     dem
    -0.48
    :
    -0.48
     bet
    -0.48
     sal
    -0.48
     e
    -0.47
     na
    -0.47
     Ch
    -0.46
    POSITIVE LOGITS
     myſelf
    0.95
     itſelf
    0.89
     الرياضيه
    0.85
    tagHelperRunner
    0.80
     }}$}
    0.80
    uxxxx
    0.79
    Location
    0.78
     Efq
    0.77
     themſelves
    0.77
     ſche
    0.77
    Act Density 0.015%

    No Known Activations