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

    Neuronpedia

    INDEX
    Explanations

    terms related to military actions, specifically focusing on disarmament and arming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.74
    lap
    -0.67
     medial
    -0.67
    pants
    -0.64
    orb
    -0.63
    acent
    -0.63
    area
    -0.62
    abyte
    -0.62
    atta
    -0.61
    aminer
    -0.61
    POSITIVE LOGITS
    ament
    1.28
    aments
    1.02
    chair
    0.98
    atures
    0.96
    ingly
    0.88
    ageddon
    0.83
    amental
    0.79
    chairs
    0.76
    ãĥ¯
    0.75
    oise
    0.73
    Act Density 0.010%

    No Known Activations