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

    Neuronpedia

    INDEX
    Explanations

    terms related to arrests and legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essages
    -0.15
    arily
    -0.14
    rov
    -0.14
     Runner
    -0.14
    acre
    -0.14
    θοÏĤ
    -0.14
    arity
    -0.14
    irsch
    -0.14
    unu
    -0.14
    omu
    -0.14
    POSITIVE LOGITS
    ante
    0.15
    akte
    0.14
    -License
    0.14
    peria
    0.14
    oleon
    0.14
    epam
    0.14
    ipeg
    0.14
     Redistribution
    0.14
    wick
    0.14
    baum
    0.13
    Act Density 0.019%

    No Known Activations