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

    Neuronpedia

    INDEX
    Explanations

    character descriptions and attributes, particularly relating to arrogance or confidence

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

    character names and traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Condol
    -0.42
    WithIOException
    -0.38
    EnableWeb
    -0.38
    IntoConstraints
    -0.37
    Diwedd
    -0.36
     Noire
    -0.36
     ProtoMessage
    -0.34
    Hentet
    -0.34
     disambiguazione
    -0.34
     فريبيس
    -0.33
    POSITIVE LOGITS
    SourceChecksum
    0.68
     carelessly
    0.51
     grinning
    0.50
     cocky
    0.49
     shouts
    0.48
     teasing
    0.47
     entertained
    0.47
     giggling
    0.47
     grinned
    0.47
     playful
    0.47
    Act Density 0.044%

    No Known Activations