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

    Neuronpedia

    INDEX
    Explanations

    references to terrorism and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    extremism terrorism IED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     démocratique
    -0.36
     peuples
    -0.34
     skå
    -0.33
     malheure
    -0.32
    Composição
    -0.32
    chenkt
    -0.31
     decorativas
    -0.31
     malheureux
    -0.31
     Grecs
    -0.31
     usaha
    -0.30
    POSITIVE LOGITS
    innoc
    0.63
     beſte
    0.59
    terrorism
    0.57
     ujednoznacz
    0.57
     terrorism
    0.57
     IED
    0.56
     المعيارى
    0.56
     bombings
    0.55
     extremism
    0.55
     trainees
    0.54
    Act Density 0.009%

    No Known Activations