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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to mathematical concepts and engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racy
    -0.62
     Bet
    -0.57
     
    -0.54
     (
    -0.53
     area
    -0.52
    GED
    -0.52
     op
    -0.51
    חים
    -0.48
     A
    -0.48
     So
    -0.48
    POSITIVE LOGITS
     Monfieur
    1.21
     Diſ
    1.03
     Anſ
    1.03
     Efq
    0.98
     Reſ
    0.97
     myſelf
    0.97
     Theſe
    0.94
     pleaſure
    0.91
     Eſ
    0.90
    ſelf
    0.89
    Act Density 0.186%

    No Known Activations