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

    Neuronpedia

    INDEX
    Explanations

    references to victims in various contexts, particularly related to crime and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aber
    -0.16
    ald
    -0.16
    vid
    -0.15
    agg
    -0.15
    orus
    -0.14
    ider
    -0.14
    alm
    -0.14
    eg
    -0.14
    mates
    -0.14
    /video
    -0.14
    POSITIVE LOGITS
    peon
    0.18
    hood
    0.16
    нÑĤ
    0.15
     versa
    0.15
    ivors
    0.15
    OLUME
    0.15
    nave
    0.15
    /mock
    0.15
    elist
    0.15
     dụng
    0.14
    Act Density 0.019%

    No Known Activations