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

    Neuronpedia

    INDEX
    Explanations

    expressions and terms related to justification and rationalization

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

    explaining or defending actions and decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.68
     Normdatei
    -0.60
     surla
    -0.57
    ActionCreators
    -0.46
    bolista
    -0.45
     AssemblyCulture
    -0.45
     <<<<<<<<<<<<<<
    -0.43
    IsMutable
    -0.41
    :✨
    -0.41
    InitVars
    -0.40
    POSITIVE LOGITS
     justification
    0.93
     justifying
    0.90
     gius
    0.88
     justifies
    0.87
     justify
    0.83
     justified
    0.81
     justific
    0.79
     Justification
    0.77
     defended
    0.73
    Justification
    0.69
    Act Density 0.102%

    No Known Activations