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

    Neuronpedia

    INDEX
    Explanations

    terms related to violence and harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    saraba
    -0.62
    Portail
    -0.57
    SharedCtor
    -0.56
    TagHelper
    -0.53
    iredo
    -0.53
    MessageOf
    -0.50
    WithIOException
    -0.49
    TextHelper
    -0.49
    digans
    -0.48
    éis
    -0.48
    POSITIVE LOGITS
     instantly
    0.65
     rumbling
    0.64
     frantically
    0.61
     violently
    0.60
     countless
    0.60
     endless
    0.60
     bursts
    0.60
    SOUNDBITE
    0.60
    KommentareTeilen
    0.60
     boom
    0.60
    Act Density 0.091%

    No Known Activations