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

    Neuronpedia

    INDEX
    Explanations

    references to terrorist incidents and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oulos
    -0.15
    assic
    -0.15
    674
    -0.14
    _placement
    -0.14
    ofire
    -0.14
    motion
    -0.14
     Tet
    -0.14
     Bender
    -0.13
    ettel
    -0.13
     McGr
    -0.13
    POSITIVE LOGITS
     Prevent
    0.30
     Counter
    0.29
     counter
    0.28
     MI
    0.26
    Counter
    0.25
     extremism
    0.24
     Ext
    0.24
    counter
    0.23
     grooming
    0.22
    MI
    0.22
    Act Density 0.012%

    No Known Activations