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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with conflict of interest and non-standard scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chofe
    -1.17
     itſelf
    -1.13
     becauſe
    -1.13
     myſelf
    -1.11
     Efq
    -1.11
     Monfieur
    -1.08
     auffi
    -1.07
     ainfi
    -1.05
     purpoſe
    -1.03
     pleaſure
    -1.01
    POSITIVE LOGITS
     trans
    0.81
     ‘
    0.74
    Билгалдахарш
    0.72
     '
    0.69
     Trans
    0.67
     major
    0.66
     non
    0.65
    aarrggbb
    0.61
    balleur
    0.61
    :\/\/
    0.61
    Act Density 0.108%

    No Known Activations