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

    Neuronpedia

    INDEX
    Explanations

    terms related to military actions and strategies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military actions and nuclear threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Costume
    -0.65
     TED
    -0.61
     Favorite
    -0.58
     Celebr
    -0.52
     Cosponsors
    -0.52
     Theme
    -0.52
     Doodle
    -0.52
    advertisement
    -0.51
     Blog
    -0.50
     Podcast
    -0.49
    POSITIVE LOGITS
     elsewhere
    0.83
     theirs
    0.83
    etheless
    0.78
     anyway
    0.76
     someday
    0.75
     outright
    0.70
     anymore
    0.70
     anyways
    0.69
     sooner
    0.69
     altogether
    0.66
    Act Density 1.166%

    No Known Activations