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

    Neuronpedia

    INDEX
    Explanations

    references to destruction or acts of destruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to destruction and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pull
    -0.79
    oft
    -0.77
    tips
    -0.73
    eret
    -0.68
    akeru
    -0.67
    soDeliveryDate
    -0.67
    Ask
    -0.66
     easing
    -0.66
    orney
    -0.66
    oult
    -0.66
    POSITIVE LOGITS
     entire
    0.87
     monuments
    0.79
     havoc
    0.78
     carc
    0.78
     habitat
    0.77
     Colossus
    0.77
     inciner
    0.75
     barriers
    0.75
     Leviathan
    0.75
     habitats
    0.74
    Act Density 0.292%

    No Known Activations