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

    Neuronpedia

    INDEX
    Explanations

    topics or discussions that have generated high levels of controversy or disagreement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lasses
    -0.55
    urances
    -0.55
    estone
    -0.54
    itors
    -0.54
    CHQ
    -0.53
    eele
    -0.52
    itor
    -0.50
    urance
    -0.50
    emouth
    -0.49
    avement
    -0.49
    POSITIVE LOGITS
    naire
    0.74
     arose
    0.71
     arises
    0.70
    naires
    0.69
     erupted
    0.69
     arising
    0.68
     surrounding
    0.65
     raged
    0.64
     flared
    0.64
     erupt
    0.63
    Act Density 6.529%

    No Known Activations