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

    Neuronpedia

    INDEX
    Explanations

    references to judgment and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.55
    }{*}{}
    -0.45
    中略
    -0.43
     thereto
    -0.41
    isome
    -0.40
    lím
    -0.40
     perhaps
    -0.39
    følgelig
    -0.38
    >";
    -0.38
    ']);
    -0.38
    POSITIVE LOGITS
     shameless
    0.60
    ACHUSET
    0.53
     Administrativna
    0.52
    Chham
    0.52
     slapped
    0.48
     fucking
    0.48
     motherfucker
    0.47
     fucked
    0.45
     miserably
    0.44
     cuck
    0.44
    Act Density 0.066%

    No Known Activations