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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something as possessing a high degree of a certain quality

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nia
    -0.78
    psons
    -0.70
    sha
    -0.66
    eto
    -0.66
    busters
    -0.65
     Miracle
    -0.65
    okia
    -0.65
    ovie
    -0.65
    alysis
    -0.64
     blindness
    -0.63
    POSITIVE LOGITS
     regarded
    1.07
     educated
    0.99
     improbable
    0.98
     publicized
    0.98
     unlikely
    0.97
     anticipated
    0.94
     skilled
    0.93
     valued
    0.90
     prized
    0.89
     acclaimed
    0.89
    Act Density 0.029%

    No Known Activations