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

    Neuronpedia

    INDEX
    Explanations

    references to various types of poisons and toxicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noqa
    -0.64
     تضيفلها
    -0.61
     tweed
    -0.57
     Савез
    -0.55
     Tweed
    -0.53
    glMatrixMode
    -0.53
    IsMutable
    -0.52
     TextAlign
    -0.51
    ,‎
    -0.50
    orsese
    -0.50
    POSITIVE LOGITS
     poisonous
    1.04
     poison
    1.04
     poisoning
    1.00
    poison
    0.99
     dangerous
    0.97
     deadly
    0.96
     Poison
    0.95
     Deadly
    0.95
    Poison
    0.93
    Deadly
    0.90
    Act Density 0.291%

    No Known Activations