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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and associated formatting, particularly in data or reference contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     diphtheria
    -0.72
     noires
    -0.65
     Tiberius
    -0.63
     Khrushchev
    -0.61
    ButterKnife
    -0.60
     tubercle
    -0.58
     Jérusalem
    -0.58
     médicale
    -0.57
     canina
    -0.57
     immortality
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.68
     WebDriverWait
    0.68
    '],
    0.66
    '},
    0.66
    "],
    0.64
     %),
    0.63
    {{$
    0.60
    +%
    0.59
    `,
    0.59
    ступи
    0.59
    Act Density 0.059%

    No Known Activations