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

    Neuronpedia

    INDEX
    Explanations

    names or terms that include the letters "K" and "r" together

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    UCT
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
     GOODMAN
    -0.65
     Canterbury
    -0.62
     ay
    -0.62
     Eleven
    -0.59
     INTO
    -0.59
     Cortana
    -0.59
     Duterte
    -0.58
     Houth
    -0.58
    POSITIVE LOGITS
    zynski
    1.49
    inski
    1.44
    owski
    1.31
    ovsky
    1.22
    owicz
    1.16
    owsky
    1.16
    ewski
    1.14
    kowski
    1.14
    sky
    1.14
    nik
    1.12
    Act Density 0.192%

    No Known Activations