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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    NB
    -0.86
    bg
    -0.80
    Alert
    -0.77
    helm
    -0.76
    another
    -0.74
    aido
    -0.73
    otte
    -0.72
    restling
    -0.71
    zilla
    -0.70
    cook
    -0.69
    POSITIVE LOGITS
     greatest
    1.19
     majority
    1.19
     predominant
    1.18
     quickest
    1.15
     wealthiest
    1.14
     safest
    1.12
     simplest
    1.12
     easiest
    1.12
     vast
    1.09
     stakes
    1.09
    Act Density 0.314%

    No Known Activations