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

    Neuronpedia

    INDEX
    Explanations

    references to criminal behavior and legal cases involving suspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.18
    ucch
    -0.16
    iba
    -0.15
    inas
    -0.15
    ÙĦÙħÙĩ
    -0.15
     fallen
    -0.15
    uentes
    -0.14
     Fallen
    -0.14
    689
    -0.14
     fal
    -0.14
    POSITIVE LOGITS
     amb
    0.24
     slit
    0.24
     targeted
    0.19
     committed
    0.19
     attacked
    0.18
     targeting
    0.18
     corner
    0.18
     target
    0.18
     prey
    0.17
     COMMIT
    0.17
    Act Density 0.084%

    No Known Activations