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

    Neuronpedia

    INDEX
    Explanations

    terms related to arms or armaments

    oai_token-act-pair · gpt-3.5-turbo

    references to "arm."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sound
    -0.75
     Dough
    -0.74
     Vide
    -0.71
    ween
    -0.68
    due
    -0.66
     Atmosp
    -0.64
    iculty
    -0.63
     Stories
    -0.63
    BUR
    -0.60
    gres
    -0.60
    POSITIVE LOGITS
    chair
    1.42
    aments
    1.42
    ament
    1.40
    ageddon
    1.30
    chairs
    1.09
    illary
    1.05
    strap
    0.99
    ando
    0.93
    ature
    0.92
    amental
    0.90
    Act Density 0.022%

    No Known Activations