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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be," indicating states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scolaires
    -0.54
     énergé
    -0.53
     démocr
    -0.52
     prato
    -0.51
    書いた
    -0.51
     encodes
    -0.50
     ברי
    -0.49
     okol
    -0.49
    sili
    -0.48
     kropp
    -0.48
    POSITIVE LOGITS
    )++;
    0.82
    utnik
    0.82
     now
    0.72
    ++]=
    0.69
    SourceChecksum
    0.69
     autorytatywna
    0.69
     currently
    0.68
     trying
    0.68
    "])
    0.67
     working
    0.65
    Act Density 0.182%

    No Known Activations