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

    Neuronpedia

    INDEX
    Explanations

    expressions of comprehension and awareness related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.63
    zości
    -0.61
    ot
    -0.61
    番
    -0.59
    الثة
    -0.58
    promo
    -0.58
     promo
    -0.57
     Pokies
    -0.57
     Grossman
    -0.56
     TRIB
    -0.56
    POSITIVE LOGITS
     Understand
    1.90
     understand
    1.89
    understand
    1.88
     understanding
    1.86
    Understand
    1.85
     understands
    1.83
     understood
    1.71
    understanding
    1.71
    understood
    1.65
     understandings
    1.64
    Act Density 0.063%

    No Known Activations