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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     each
    -0.62
     normal
    -0.57
     free
    -0.55
    enterian
    -0.55
     BOTH
    -0.54
    hele
    -0.54
     leg
    -0.54
    acı
    -0.53
     any
    -0.53
    hotra
    -0.53
    POSITIVE LOGITS
     nakalista
    0.76
    OGND
    0.72
     kasarigan
    0.69
    ագրություններ
    0.67
    Hentet
    0.67
     дописавши
    0.66
    ]$}
    0.64
    __);
    0.63
    }();
    0.62
    })$}
    0.61
    Act Density 0.132%

    No Known Activations