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

    Neuronpedia

    INDEX
    Explanations

    words related to recognition and identifying patterns or structures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    berries
    -0.60
    xit
    -0.59
    lla
    -0.59
     ox
    -0.55
     Tone
    -0.54
     Diver
    -0.54
    ritch
    -0.51
    hire
    -0.50
     Grind
    -0.49
    llo
    -0.49
    POSITIVE LOGITS
    recogn
    0.95
    izable
    0.88
    isable
    0.86
    essed
    0.79
    ition
    0.78
     recognition
    0.76
    gements
    0.69
    usable
    0.66
    isance
    0.65
    ances
    0.65
    Act Density 4.633%

    No Known Activations