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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe levels of quality, service, or skill

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    new
    -0.61
    New
    -0.57
    wi
    -0.57
     
    -0.54
    U
    -0.53
     New
    -0.53
     new
    -0.53
     negativa
    -0.52
    '
    -0.52
    Positives
    -0.51
    POSITIVE LOGITS
     levels
    1.33
    Levels
    1.27
     level
    1.27
     Levels
    1.21
     poziom
    1.18
    levels
    1.17
     LEVELS
    1.15
     LEVEL
    1.15
    LEVEL
    1.13
    niveau
    1.12
    Act Density 0.209%

    No Known Activations