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

    Neuronpedia

    INDEX
    Explanations

    incidents and events related to violence and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dden
    -0.15
     Incoming
    -0.15
    Incoming
    -0.14
     Misc
    -0.14
    agh
    -0.14
    ngör
    -0.14
    _NOTICE
    -0.14
    راÙĩ
    -0.14
     polož
    -0.13
    สà¸Ķ
    -0.13
    POSITIVE LOGITS
     involving
    0.28
     investigation
    0.22
     believed
    0.21
     investigated
    0.19
     involve
    0.19
     occurred
    0.18
     involves
    0.18
     reported
    0.17
     xảy
    0.17
    æ¶ī
    0.17
    Act Density 0.098%

    No Known Activations