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

    Neuronpedia

    INDEX
    Explanations

    references to corresponding items or values in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.63
    AxisAlignment
    -0.63
    phosa
    -0.58
     AppCompatTheme
    -0.55
    klaim
    -0.52
     nltk
    -0.52
     scrollView
    -0.50
     walking
    -0.48
    ссора
    -0.48
     newItem
    -0.48
    POSITIVE LOGITS
     corresponding
    1.33
    corresponding
    1.20
    Corresponding
    1.08
     Corresponding
    1.06
     respective
    1.04
     entsprechende
    1.03
     correspondiente
    1.02
     relevant
    1.00
    相应
    1.00
     entsprechenden
    1.00
    Act Density 0.374%

    No Known Activations