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

    Neuronpedia

    INDEX
    Explanations

    instances of analysis and functional evaluation in mathematical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    cies
    -0.07
    taire
    -0.07
    LATED
    -0.06
    sled
    -0.06
    $__
    -0.06
    lfw
    -0.06
     emphasis
    -0.06
     Tent
    -0.06
    ensus
    -0.06
    ä¸Ī
    -0.06
    POSITIVE LOGITS
    uben
    0.07
    ela
    0.07
     how
    0.07
    Decorator
    0.07
     relationships
    0.07
    aight
    0.07
     behavior
    0.07
    znik
    0.06
    roid
    0.06
     PROFITS
    0.06
    Act Density 0.065%

    No Known Activations