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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or markers related to data structures and file formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.77
     kasarigan
    -0.61
    verifyException
    -0.53
     للمعارف
    -0.50
    featureID
    -0.49
    MockBean
    -0.49
     informée
    -0.47
    awakeFromNib
    -0.44
    erdings
    -0.43
    Hochspringen
    -0.42
    POSITIVE LOGITS
     Stan
    0.56
    Stan
    0.52
     stan
    0.52
     Stanley
    0.50
    Stanley
    0.47
     Princess
    0.47
     Carrier
    0.47
     Rick
    0.46
     Stra
    0.45
     SS
    0.45
    Act Density 1.612%

    No Known Activations