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

    Neuronpedia

    INDEX
    Explanations

    references to groups of items or entities, especially in a comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addComponent
    -0.79
     Kleidung
    -0.61
    PathVariable
    -0.60
     Dul
    -0.59
     있다
    -0.59
     ότι
    -0.59
     informaci
    -0.58
    pragma
    -0.56
    nextSibling
    -0.55
     concor
    -0.55
    POSITIVE LOGITS
     these
    2.57
    These
    2.26
    these
    2.26
     These
    2.18
     THESE
    2.12
    这些
    1.75
    這些
    1.67
     theses
    1.64
     Theſe
    1.62
    Estos
    1.61
    Act Density 0.120%

    No Known Activations