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

    Neuronpedia

    INDEX
    Explanations

    information related to "depending on" a particular factor or variable

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    vision
    -0.93
    posted
    -0.77
    code
    -0.77
    talk
    -0.77
    mark
    -0.76
    blue
    -0.75
    se
    -0.75
    anas
    -0.75
    arest
    -0.74
    marks
    -0.74
    POSITIVE LOGITS
     conting
    0.76
     depending
    0.70
     degrees
    0.70
     facult
    0.70
     hypot
    0.69
     upon
    0.69
     arrang
    0.69
     unden
    0.69
     occas
    0.69
     configurations
    0.69
    Act Density 6.899%

    No Known Activations