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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing violent actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veto
    -0.70
     postponed
    -0.63
    allowed
    -0.62
    eton
    -0.62
    hur
    -0.62
    orea
    -0.61
    cens
    -0.61
     offensively
    -0.60
     vetoed
    -0.58
    chall
    -0.58
    POSITIVE LOGITS
     Pieces
    1.01
     pieces
    0.88
     paste
    0.84
     fragments
    0.84
     rubble
    0.80
    utonium
    0.80
     shred
    0.79
    ãĤ©
    0.76
    ffee
    0.73
     powder
    0.71
    Act Density 0.251%

    No Known Activations