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

    Neuronpedia

    INDEX
    Explanations

    key terms related to significance and ranking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odule
    -0.15
    insky
    -0.14
    -0.14
    slideDown
    -0.14
    ecessarily
    -0.14
    _parms
    -0.13
    entials
    -0.13
     respective
    -0.13
    ollar
    -0.13
    orie
    -0.13
    POSITIVE LOGITS
     thing
    0.40
    thing
    0.30
     question
    0.29
     Thing
    0.27
    Thing
    0.26
     reason
    0.26
     benefit
    0.21
     advantage
    0.20
     challenge
    0.19
     lesson
    0.19
    Act Density 0.188%

    No Known Activations