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

    Neuronpedia

    INDEX
    Explanations

    words related to military strategy and technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mas
    -0.61
    con
    -0.61
    beat
    -0.59
    agar
    -0.59
    fur
    -0.57
    hon
    -0.57
    com
    -0.55
    Press
    -0.55
    Inv
    -0.54
    aff
    -0.54
    POSITIVE LOGITS
     theirs
    0.74
     something
    0.66
     another
    0.64
     lots
    0.64
     hers
    0.63
     them
    0.62
     multiple
    0.59
     him
    0.59
     THEM
    0.58
     anything
    0.58
    Act Density 21.392%

    No Known Activations