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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ships
    -0.91
    osponsors
    -0.88
    ooks
    -0.87
    lems
    -0.83
    inders
    -0.83
    hips
    -0.80
    estones
    -0.80
    uits
    -0.78
    ories
    -0.77
    lations
    -0.77
    POSITIVE LOGITS
     unnamed
    1.12
     woman
    1.10
     participant
    0.99
     commenter
    0.97
     person
    0.94
     protester
    0.94
     unidentified
    0.93
     caller
    0.92
     elderly
    0.91
     man
    0.89
    Act Density 0.103%

    No Known Activations