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

    Neuronpedia

    INDEX
    Explanations

    references to community safety measures and infrastructure issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ROLLER
    -0.16
     Fucked
    -0.15
    changer
    -0.15
    printing
    -0.15
    printer
    -0.15
    OKIE
    -0.15
     Folding
    -0.15
    checker
    -0.15
    Knife
    -0.15
    jte
    -0.15
    POSITIVE LOGITS
     flash
    0.25
     glow
    0.23
     kick
    0.23
     knock
    0.23
     rush
    0.22
     lock
    0.22
     crash
    0.22
     punch
    0.22
     drain
    0.22
     melt
    0.22
    Act Density 0.083%

    No Known Activations