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

    Neuronpedia

    INDEX
    Explanations

    references to military or combat-related activities

    oai_token-act-pair · gpt-3.5-turbo

    information related to military actions and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.83
     millennials
    -0.76
     audi
    -0.73
     Marvel
    -0.72
     Autism
    -0.72
     Oprah
    -0.70
     endors
    -0.67
     congr
    -0.67
     STEM
    -0.65
     Journals
    -0.64
    POSITIVE LOGITS
     raiding
    1.00
     themselves
    0.94
     artillery
    0.89
    numbered
    0.88
     armoured
    0.88
     outnumbered
    0.86
    ilitary
    0.85
     raided
    0.85
     seizing
    0.84
     besie
    0.83
    Act Density 0.732%

    No Known Activations