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

    Neuronpedia

    INDEX
    Explanations

    articles and common determiners in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inmueble
    -0.64
     sonno
    -0.63
     cálido
    -0.61
     précie
    -0.60
     således
    -0.59
     ciasc
    -0.59
     ragioni
    -0.58
     dermed
    -0.56
     terecht
    -0.56
    niksi
    -0.56
    POSITIVE LOGITS
     kasarigan
    0.85
     thing
    0.79
    دانشنامهٔ
    0.77
     stupid
    0.76
     guy
    0.74
     whole
    0.72
    other
    0.71
     crappy
    0.71
     WHOLE
    0.69
     ones
    0.68
    Act Density 0.581%

    No Known Activations