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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments or affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compañ
    -0.99
     Monfieur
    -0.89
    -0.88
    #+#
    -0.88
     Walkover
    -0.87
     Efq
    -0.85
     Malk
    -0.85
     itſelf
    -0.85
     cire
    -0.82
    munk
    -0.81
    POSITIVE LOGITS
    pos
    1.38
     Pos
    1.28
     pos
    1.16
    Pos
    1.15
     POS
    1.13
    POS
    1.06
    setPos
    0.96
    getPos
    0.91
    BlockPos
    0.82
    Gonna
    0.77
    Act Density 0.027%

    No Known Activations