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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a small amount or degree of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    inarily
    -0.79
    itures
    -0.75
    idth
    -0.74
    ocity
    -0.69
    iership
    -0.69
    æ©
    -0.67
    ovies
    -0.67
    apons
    -0.67
    velt
    -0.66
    endars
    -0.66
    POSITIVE LOGITS
    umen
    0.87
    terness
    0.80
     bit
    0.76
    ener
    0.73
     prick
    0.70
     aspirin
    0.68
    wig
    0.67
     overboard
    0.67
     luck
    0.65
    mask
    0.64
    Act Density 0.023%

    No Known Activations