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

    Neuronpedia

    INDEX
    Explanations

    occurrences of utility functions or related terms

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

    util

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fotográfico
    -0.47
     aparcamiento
    -0.41
     Mindest
    -0.39
     fotográfica
    -0.39
    fattning
    -0.38
    PageNumber
    -0.38
    ________________
    -0.38
    <strong>
    -0.36
     söz
    -0.36
    StartTag
    -0.36
    POSITIVE LOGITS
     util
    2.14
     Util
    1.83
    util
    1.61
    Util
    1.41
     utilitarian
    1.38
     UTIL
    1.31
    UTIL
    1.30
     utility
    1.24
     Utili
    1.14
     Utility
    1.12
    Act Density 0.008%

    No Known Activations