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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HostException
    -0.81
     للمعارف
    -0.72
     հղումներ
    -0.69
    ConstraintMaker
    -0.69
    TypedDataSet
    -0.66
     Normdatei
    -0.65
    adaptiveStyles
    -0.65
     GeoNames
    -0.64
    NewUrlParser
    -0.64
     Infórmanos
    -0.63
    POSITIVE LOGITS
    textbackslash
    0.48
     fhew
    0.48
     Section
    0.47
     progress
    0.47
    nutie
    0.47
     launch
    0.45
     one
    0.45
    Section
    0.44
     grass
    0.44
     namin
    0.44
    Act Density 0.009%

    No Known Activations