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

    Neuronpedia

    INDEX
    Explanations

    references to acts of killing or murder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    906
    -0.16
    igo
    -0.15
    esta
    -0.14
    duto
    -0.14
    alo
    -0.14
    odes
    -0.14
    neider
    -0.13
    DAL
    -0.13
    -way
    -0.13
    ummings
    -0.13
    POSITIVE LOGITS
    ábado
    0.18
    \Php
    0.15
    -death
    0.15
    kö
    0.15
    abyrin
    0.15
    ayscale
    0.14
    ked
    0.14
    throp
    0.14
     Jennings
    0.14
    plotlib
    0.14
    Act Density 0.058%

    No Known Activations