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

    Neuronpedia

    INDEX
    Explanations

    terms related to duality and comparative concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.66
    ConstraintMaker
    -0.64
     betweenstory
    -0.64
     snippetHide
    -0.61
    évaluateur
    -0.61
     kasarigan
    -0.56
    })));
    -0.56
     مشين
    -0.54
    ArrowToggle
    -0.54
    addGap
    -0.53
    POSITIVE LOGITS
     side
    3.86
     Side
    3.04
    side
    2.98
    Side
    2.95
     SIDE
    2.91
    SIDE
    2.48
     sides
    2.33
     lado
    2.25
     côté
    1.97
     Seite
    1.94
    Act Density 0.754%

    No Known Activations