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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military operations and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "offensive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chell
    -0.88
    aido
    -0.80
     Solitaire
    -0.79
    Deal
    -0.79
    bourg
    -0.78
    ilk
    -0.76
    cling
    -0.73
    hyde
    -0.70
    arent
    -0.69
    trust
    -0.67
    POSITIVE LOGITS
     offensive
    0.98
     linemen
    0.90
     lineman
    0.78
     thrust
    0.74
    offensive
    0.71
     offense
    0.71
     contraceptives
    0.70
     contraception
    0.69
     assault
    0.69
    ity
    0.69
    Act Density 0.015%

    No Known Activations