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

    Neuronpedia

    INDEX
    Explanations

    incidents related to violent events and fires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.17
    isset
    -0.14
    _NOTICE
    -0.14
     lying
    -0.14
     ARR
    -0.13
    สà¸Ķ
    -0.13
    opa
    -0.13
    ayer
    -0.13
    irl
    -0.13
    ARR
    -0.13
    POSITIVE LOGITS
     involving
    0.39
     involve
    0.26
     involves
    0.25
     targeting
    0.22
     investigated
    0.21
     investigation
    0.21
     believed
    0.20
    æ¶ī
    0.20
     claimed
    0.20
     involvement
    0.19
    Act Density 0.116%

    No Known Activations