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

    Neuronpedia

    INDEX
    Explanations

    occurrences of violence and conflict involving groups and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«ãĥī
    -0.17
    656
    -0.16
    659
    -0.16
    crew
    -0.14
    HAND
    -0.14
    bubble
    -0.14
    رز
    -0.14
     explo
    -0.14
    irus
    -0.14
    è¯
    -0.14
    POSITIVE LOGITS
     burn
    0.24
     torch
    0.23
     storm
    0.23
     burned
    0.22
    burn
    0.21
     burning
    0.21
     burnt
    0.21
     block
    0.20
     pill
    0.20
    storm
    0.20
    Act Density 0.124%

    No Known Activations