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

    Neuronpedia

    INDEX
    Explanations

    instances of modifiers that indicate frequency or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.70
    adors
    -0.63
     fevere
    -0.63
    ">'.$
    -0.61
     tartalomajánló
    -0.58
    πάρχ
    -0.57
     Theſe
    -0.57
    Parcelize
    -0.57
    zbęd
    -0.56
    lanmış
    -0.56
    POSITIVE LOGITS
    Mainly
    0.65
    mainly
    0.61
     mainly
    0.61
    ArrowToggle
    0.61
     Mainly
    0.61
     nakalista
    0.58
    marily
    0.58
     Particularly
    0.58
    ticularly
    0.57
    Especially
    0.57
    Act Density 0.443%

    No Known Activations