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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating uniqueness and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiennent
    -0.70
     piele
    -0.65
     mourut
    -0.64
     religieuses
    -0.63
     connaissent
    -0.63
     alguno
    -0.62
     connues
    -0.61
     esetén
    -0.59
     dysplasia
    -0.59
     nationales
    -0.57
    POSITIVE LOGITS
    SourceChecksum
    0.98
    ".
    0.89
     ';
    0.85
     '{@
    0.83
    %");
    0.79
    исленность
    0.79
    %";
    0.77
    ')):
    0.76
    )');
    0.76
    LookAnd
    0.75
    Act Density 0.718%

    No Known Activations