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

    Neuronpedia

    INDEX
    Explanations

    references to violence and warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MC
    -0.16
    389
    -0.15
    pector
    -0.15
    Grow
    -0.15
    522
    -0.15
    587
    -0.14
    à¹Ģสร
    -0.14
    155
    -0.14
    defer
    -0.14
    naires
    -0.14
    POSITIVE LOGITS
    ãĤ¯
    0.16
    -INF
    0.14
    inator
    0.14
    ê°ĢìļĶ
    0.14
    ái
    0.14
    hub
    0.13
    алиÑģÑĤ
    0.13
    alf
    0.13
    fuse
    0.13
    zburg
    0.13
    Act Density 0.355%

    No Known Activations