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

    Neuronpedia

    INDEX
    Explanations

    expressions of sentiment or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assertEqual
    -0.61
    verket
    -0.60
     Aar
    -0.60
    TryParse
    -0.60
    Capricorn
    -0.60
    جویان
    -0.59
     Dumnezeu
    -0.58
    婪
    -0.58
    циони
    -0.57
     octavo
    -0.57
    POSITIVE LOGITS
     expressions
    1.17
    EXPRESS
    1.09
    Expressions
    1.05
     EXPRESS
    1.04
     Expressions
    1.04
     expr
    1.03
     expression
    1.01
    expressions
    0.99
    Express
    0.98
     Expression
    0.96
    Act Density 0.149%

    No Known Activations