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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressions of emotion and morality

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

    technical or specialized terminology in academic, scientific, or formal procedural contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @melissawessel91

    technical writing

    np_max-act-logits · claude-4-5-sonnetTriggered by @melissawessel91
    New Auto-Interp
    Negative Logits
    Personensuche
    -2.27
     Савезне
    -1.63
    tagHelperRunner
    -1.60
     Мексичка
    -1.56
    :✨
    -1.54
    LookAnd
    -1.46
     autorytatywna
    -1.45
    adaptiveStyles
    -1.43
    SourceChecksum
    -1.41
    setVerticalGroup
    -1.40
    POSITIVE LOGITS
     
    0.85
     […]
    0.72
    ↵
    0.68
      
    0.62
     ...
    0.60
    '
    0.58
    ,
    0.58
     A
    0.57
     (
    0.57
     S
    0.56
    Act Density 97.755%

    No Known Activations