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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms that indicate position or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥ³
    -0.14
    Multiplicity
    -0.13
    andatory
    -0.13
    azzi
    -0.13
    itored
    -0.13
    abela
    -0.13
     dara
    -0.13
    ener
    -0.13
    nock
    -0.13
    iere
    -0.13
    POSITIVE LOGITS
     firmly
    0.47
     squarely
    0.43
     solid
    0.39
    firm
    0.38
     square
    0.38
    square
    0.36
     SQUARE
    0.35
     Square
    0.34
    -square
    0.34
     Firm
    0.33
    Act Density 0.125%

    No Known Activations