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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or habitual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ειν
    -0.65
    WriteLine
    -0.64
     Potsdam
    -0.63
     Descubre
    -0.60
    !("{
    -0.59
    classnames
    -0.58
     אד
    -0.57
     thoát
    -0.56
     iParam
    -0.55
    flik
    -0.55
    POSITIVE LOGITS
     solito
    1.05
     usually
    0.95
    Usual
    0.94
     Usually
    0.92
    Usually
    0.87
     propOrder
    0.84
     üb
    0.83
     Typically
    0.81
    UALLY
    0.81
     suele
    0.81
    Act Density 0.088%

    No Known Activations