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

    Neuronpedia

    INDEX
    Explanations

    control actions and settings related to adjustment and customization

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    deals
    -0.79
    ands
    -0.75
    ublic
    -0.74
    humans
    -0.72
    meet
    -0.72
    geries
    -0.72
    ebook
    -0.72
    gin
    -0.71
    andro
    -0.71
    blogs
    -0.71
    POSITIVE LOGITS
     amount
    1.63
     width
    1.58
     duration
    1.56
     thickness
    1.55
     length
    1.54
     diameter
    1.53
     size
    1.53
     number
    1.49
     radius
    1.47
     height
    1.46
    Act Density 0.358%

    No Known Activations