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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.60
    routeProvider
    -0.56
    PreInfinity
    -0.56
     ocurrido
    -0.54
     ویکی‌پدی
    -0.53
     Talvez
    -0.53
     esternos
    -0.51
    -------
    -0.51
    '}>
    -0.49
    '},
    -0.48
    POSITIVE LOGITS
     very
    0.94
     again
    0.92
     muito
    0.76
     everyone
    0.67
     guys
    0.66
    givings
    0.65
     beaucoup
    0.65
     bardzo
    0.63
     רבה
    0.62
     so
    0.62
    Act Density 0.050%

    No Known Activations