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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating improbability or unlikelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing improbability or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ravings
    -0.86
    Ü
    -0.82
    artney
    -0.79
    ocked
    -0.76
    aeper
    -0.75
    zeb
    -0.74
    autions
    -0.73
    ussion
    -0.72
    ulative
    -0.72
    oola
    -0.71
    POSITIVE LOGITS
    icably
    0.89
    theless
    0.86
    bably
    0.81
    necess
    0.74
     coincidence
    0.73
     elector
    0.72
     underestimate
    0.72
     unanim
    0.71
     necessarily
    0.70
    ties
    0.68
    Act Density 0.024%

    No Known Activations