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

    Neuronpedia

    INDEX
    Explanations

    events involving violence or terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennen
    -0.15
     hlad
    -0.15
    982
    -0.15
    elan
    -0.15
    ioso
    -0.15
    928
    -0.14
    eni
    -0.14
     cref
    -0.14
     solar
    -0.14
    olated
    -0.14
    POSITIVE LOGITS
     deton
    0.23
     blast
    0.21
    çĤ¸
    0.20
     explodes
    0.18
     Blast
    0.18
     bomb
    0.18
     Explos
    0.17
     exploded
    0.17
     explosion
    0.16
    Fuse
    0.16
    Act Density 0.029%

    No Known Activations