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

    Neuronpedia

    INDEX
    Explanations

    occurrences of error handling phrases in code snippets

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bind
    -0.37
     Weisheit
    -0.33
    primaryColor
    -0.29
     Seleccione
    -0.29
     embaraz
    -0.28
     ...
    -0.28
    default
    -0.27
     Gebrauch
    -0.27
    NamedQueries
    -0.27
    Bind
    -0.27
    POSITIVE LOGITS
    getFull
    0.90
     CreateTagHelper
    0.76
    évaluateur
    0.75
     EconPapers
    0.74
    iſchen
    0.71
    parsedMessage
    0.70
    aarrggbb
    0.69
     zwiſchen
    0.68
    rungsseite
    0.68
     disambiguazione
    0.68
    Act Density 0.000%

    No Known Activations