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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research limitations and the influence of external variables on study results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.75
    mobileqq
    -0.72
     Monfieur
    -0.69
    lapsingToolbar
    -0.69
    SharedDtor
    -0.69
    moveToFirst
    -0.69
     Roskov
    -0.67
    Geplaatst
    -0.66
    зулта
    -0.64
    RegressionTest
    -0.63
    POSITIVE LOGITS
     Partly
    1.15
     partly
    1.09
    Partly
    1.08
    partly
    1.04
     partially
    0.95
     Partially
    0.92
     parcialmente
    0.81
     extent
    0.78
    parti
    0.75
     largely
    0.71
    Act Density 0.260%

    No Known Activations