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

    Neuronpedia

    INDEX
    Explanations

    references to violence and conflict-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .must
    -0.14
    amment
    -0.14
    ossier
    -0.14
     Frag
    -0.14
    jb
    -0.14
    Bulk
    -0.13
    ियन
    -0.13
    .Annotation
    -0.13
    ronic
    -0.13
    .entries
    -0.13
    POSITIVE LOGITS
    лÑı
    0.17
    bane
    0.16
    aghan
    0.15
    uD
    0.14
    achable
    0.14
    ewed
    0.14
    olumn
    0.14
    lun
    0.13
    llum
    0.13
    ABI
    0.13
    Act Density 0.225%

    No Known Activations