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

    Neuronpedia

    INDEX
    Explanations

    computer programming terms and technical jargon

    oai_token-act-pair · gpt-3.5-turbo

    references to various media formats and creative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streng
    -0.80
     rog
    -0.79
     grit
    -0.75
     godd
    -0.72
     econom
    -0.71
     plague
    -0.71
     braking
    -0.71
     poaching
    -0.71
     strengthening
    -0.70
     sentencing
    -0.70
    POSITIVE LOGITS
    Effect
    1.36
    Menu
    1.33
    Jr
    1.33
    Mods
    1.31
    Pages
    1.30
    Exception
    1.29
    Rat
    1.29
    Rules
    1.29
    Com
    1.29
    Bed
    1.29
    Act Density 0.243%

    No Known Activations