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

    Neuronpedia

    INDEX
    Explanations

    features or attribute descriptions within text, potentially related to reviews or opinions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ibaba
    -0.50
     goose
    -0.45
     experiment
    -0.45
     sweat
    -0.45
     kin
    -0.45
    yip
    -0.44
     ut
    -0.43
    appy
    -0.43
    cale
    -0.43
     landfill
    -0.42
    POSITIVE LOGITS
    ional
    0.67
    ament
    0.56
    folio
    0.55
    ATURE
    0.55
    Writing
    0.55
    casting
    0.55
    icularly
    0.54
    orial
    0.53
    IGN
    0.53
    osition
    0.53
    Act Density 8.928%

    No Known Activations