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

    Neuronpedia

    INDEX
    Explanations

    references to comics and comic-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    484
    -0.15
     pump
    -0.15
    bias
    -0.14
    485
    -0.14
     biases
    -0.14
    çŀ
    -0.14
    ción
    -0.14
    simd
    -0.14
    amination
    -0.13
    chai
    -0.13
    POSITIVE LOGITS
     Judge
    0.28
    Judge
    0.26
     Judges
    0.22
     judge
    0.21
     strips
    0.21
    judge
    0.20
     Mega
    0.19
     Wagner
    0.18
     judges
    0.18
     Marshal
    0.17
    Act Density 0.005%

    No Known Activations