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

    Neuronpedia

    INDEX
    Explanations

    phrases that express surprise or emphasis, often beginning with 'Oh' and 'And'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BILITIES
    -0.89
    Ö¼
    -0.81
    actionDate
    -0.74
    orea
    -0.73
    alion
    -0.72
    ograp
    -0.71
    arov
    -0.71
    acters
    -0.70
    cius
    -0.69
    arlane
    -0.68
    POSITIVE LOGITS
     dear
    0.79
     gasp
    0.71
     blasphemy
    0.69
     heavens
    0.66
     yea
    0.66
     shudder
    0.63
     yes
    0.63
     horror
    0.62
     Miss
    0.61
     hurry
    0.61
    Act Density 0.054%

    No Known Activations