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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of arms or weaponry

    oai_token-act-pair · gpt-3.5-turbo

    references to arms and armaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sound
    -0.74
     Dough
    -0.70
     Vide
    -0.68
    iculty
    -0.67
    lish
    -0.65
    ween
    -0.63
     Stories
    -0.63
    BUR
    -0.62
    due
    -0.62
     Atmosp
    -0.62
    POSITIVE LOGITS
    chair
    1.48
    ament
    1.45
    aments
    1.44
    ageddon
    1.43
    chairs
    1.17
    illary
    1.04
    amental
    1.02
    atures
    0.97
    ature
    0.97
    ando
    0.95
    Act Density 0.016%

    No Known Activations