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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bénévol
    -0.47
    íč
    -0.45
     compréhen
    -0.45
     znan
    -0.44
     observación
    -0.44
     piatta
    -0.43
     renforcé
    -0.43
     osallist
    -0.43
     meditación
    -0.42
     financiamiento
    -0.42
    POSITIVE LOGITS
     que
    0.79
     hogy
    0.78
     що
    0.76
     że
    0.67
     что
    0.66
    Que
    0.65
    Що
    0.65
    DockStyle
    0.63
     أنه
    0.62
     ότι
    0.61
    Act Density 0.123%

    No Known Activations