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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions related to crime and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hou
    -0.16
     gou
    -0.16
    essen
    -0.15
    одо
    -0.15
    kB
    -0.15
    izyon
    -0.15
    ivia
    -0.14
    渡
    -0.14
    izon
    -0.14
    tg
    -0.14
    POSITIVE LOGITS
    ediÄŁi
    0.16
    iola
    0.15
    ictim
    0.14
    ês
    0.14
    368
    0.14
     Central
    0.14
    820
    0.14
    fts
    0.14
    ?action
    0.14
    634
    0.13
    Act Density 0.081%

    No Known Activations