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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "Mandelbrot" appears

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular individual or entity, specifically focusing on a pattern related to "Kandel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Furious
    -0.67
     upright
    -0.66
     shorth
    -0.65
     rout
    -0.64
     Feet
    -0.63
     bisexual
    -0.63
     Fug
    -0.62
     maritime
    -0.61
     backward
    -0.61
     Rogue
    -0.60
    POSITIVE LOGITS
    andel
    4.71
    ande
    1.21
    alloc
    0.92
    annis
    0.88
    aeda
    0.85
    icer
    0.84
    ongyang
    0.83
    attery
    0.81
     purported
    0.80
    icol
    0.78
    Act Density 0.029%

    No Known Activations