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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with various data points or measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    :+:
    -0.66
    OptionsMenu
    -0.65
     putt
    -0.64
    
    -0.63
    visiae
    -0.59
    SequentialGroup
    -0.58
     chré
    -0.58
     myſelf
    -0.57
    leyball
    -0.57
    ITHUB
    -0.57
    POSITIVE LOGITS
    gtest
    0.55
     CreateTagHelper
    0.53
     simultaneously
    0.52
    Билгалдахарш
    0.51
    WithIOException
    0.50
    ities
    0.48
    TypedValue
    0.47
     Bog
    0.47
     β
    0.46
    peen
    0.46
    Act Density 0.067%

    No Known Activations