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

    Neuronpedia

    INDEX
    Explanations

    mentions of collaboration or conflict involving multiple parties

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention various types of forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.73
    mbuds
    -0.72
     Kind
    -0.72
     Jub
    -0.68
     RTX
    -0.68
    apest
    -0.67
     Hop
    -0.67
    MAL
    -0.66
     Blessed
    -0.66
     Lifetime
    -0.66
    POSITIVE LOGITS
     forces
    1.07
     force
    1.03
     exerted
    0.86
    force
    0.83
    forces
    0.83
     troops
    0.80
    peak
    0.78
     maj
    0.78
     loyal
    0.74
     fatig
    0.74
    Act Density 0.021%

    No Known Activations