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

    Neuronpedia

    INDEX
    Explanations

    references to utility-related concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Util" or "utility"-related terms

    np_acts-logits-general · gemini-2.0-flash

    util/utility/utils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.66
     informée
    -0.65
    parsedMessage
    -0.63
    LookAnd
    -0.62
     autorytatywna
    -0.60
    httphttps
    -0.60
    ſelf
    -0.60
     Anſ
    -0.59
     CanadaChoose
    -0.58
    ſelves
    -0.58
    POSITIVE LOGITS
     Util
    0.50
     util
    0.48
     utility
    0.47
     Utility
    0.44
     Utilities
    0.43
     Utf
    0.43
     trench
    0.43
    UT
    0.42
     Ruth
    0.42
     trenches
    0.41
    Act Density 0.157%

    No Known Activations