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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of victims and victimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipo
    -0.16
    cron
    -0.16
    enta
    -0.15
    ings
    -0.15
    ep
    -0.15
    azor
    -0.15
    aru
    -0.15
    bons
    -0.15
    oes
    -0.14
    ROS
    -0.14
    POSITIVE LOGITS
    hood
    0.23
    ized
    0.21
    izers
    0.19
    andalone
    0.18
    ively
    0.18
    /target
    0.17
    izing
    0.17
    ories
    0.16
    ization
    0.16
    IZER
    0.15
    Act Density 0.019%

    No Known Activations