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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "that" and its grammatical uses in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.64
    Erfolge
    -0.58
     préf
    -0.57
    //
    -0.55
    PreExecute
    -0.55
    日閲覧
    -0.55
     indisponible
    -0.54
    Datuak
    -0.52
     préféré
    -0.51
     Púb
    -0.51
    POSITIVE LOGITS
     matter
    0.73
     excuse
    0.71
     guarantee
    0.68
     bode
    0.67
     mean
    0.64
     excuses
    0.64
     happen
    0.62
     MATTER
    0.60
     excused
    0.60
     detract
    0.60
    Act Density 0.171%

    No Known Activations