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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating comprehension or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.61
     referenties
    -0.58
    INCREF
    -0.57
    __(/*!
    -0.55
     bibliographies
    -0.54
    alse
    -0.53
    IGraphics
    -0.52
     väli
    -0.51
     Conta
    -0.51
     Cassius
    -0.51
    POSITIVE LOGITS
     understand
    1.69
    understand
    1.61
     understood
    1.57
     Understand
    1.50
     understands
    1.49
    Understand
    1.45
    understood
    1.44
     understanding
    1.43
     comprehend
    1.30
    understanding
    1.23
    Act Density 0.301%

    No Known Activations