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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dur
    -0.15
    lis
    -0.15
    -hash
    -0.15
    elf
    -0.15
    alt
    -0.15
    inas
    -0.14
     Fist
    -0.14
    ifu
    -0.14
    ender
    -0.14
    aker
    -0.14
    POSITIVE LOGITS
    strup
    0.15
    Ïħν
    0.15
     suspect
    0.15
    exercise
    0.15
    ahu
    0.15
    PÅĻÃŃ
    0.14
     Suk
    0.14
    elic
    0.14
    swer
    0.14
    wart
    0.14
    Act Density 0.008%

    No Known Activations