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

    Neuronpedia

    INDEX
    Explanations

    words associated with gradual change or progression

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Olivier
    -0.65
     pertin
    -0.65
    lès
    -0.63
    ksh
    -0.63
     okhttp
    -0.61
    setHorizontal
    -0.61
     nélk
    -0.61
     QName
    -0.60
     Dusche
    -0.59
    elry
    -0.59
    POSITIVE LOGITS
     Gradually
    0.89
     gradually
    0.87
     gradualmente
    0.85
     allmäh
    0.84
     Slowly
    0.78
    slowly
    0.78
    UserScript
    0.77
     lentamente
    0.76
    Slowly
    0.76
     gradual
    0.75
    Act Density 0.007%

    No Known Activations