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

    Neuronpedia

    INDEX
    Explanations

    words related to danger or threats

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various forms of risk or danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.65
    MQ
    -0.64
     actionGroup
    -0.61
    ovy
    -0.61
    zos
    -0.60
    chet
    -0.60
    olon
    -0.60
    ILA
    -0.58
     oun
    -0.58
    olver
    -0.56
    POSITIVE LOGITS
     financially
    0.88
     of
    0.78
    angering
    0.77
     because
    0.73
    bh
    0.71
     lest
    0.69
     posed
    0.69
     unless
    0.66
     endanger
    0.65
     from
    0.65
    Act Density 0.065%

    No Known Activations