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

    Neuronpedia

    INDEX
    Explanations

    references to murder and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĭлки
    -0.15
    ird
    -0.15
    lage
    -0.15
    asser
    -0.14
    381
    -0.14
    ÑģÑĭл
    -0.14
    REMOTE
    -0.14
    oha
    -0.14
    ersistence
    -0.14
    óln
    -0.14
    POSITIVE LOGITS
    ously
    0.23
    abilia
    0.22
    ous
    0.22
    -su
    0.21
     spree
    0.19
    joy
    0.17
     scenes
    0.16
     Scenes
    0.16
    rio
    0.15
    ÏĥÏĦη
    0.15
    Act Density 0.027%

    No Known Activations