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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to size, measurements, and physical properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    BASELINE
    -0.56
     relaxation
    -0.56
     idly
    -0.56
    intahan
    -0.55
    嬸
    -0.55
    Massive
    -0.55
     Distant
    -0.55
    distant
    -0.54
     ngoại
    -0.53
     خارجية
    -0.52
    POSITIVE LOGITS
     étro
    0.88
     tighter
    0.73
     étroite
    0.71
     narrowing
    0.69
     tight
    0.67
     tightly
    0.65
     narrower
    0.65
     narrow
    0.63
     shorter
    0.62
    narrow
    0.62
    Act Density 0.253%

    No Known Activations