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

    Neuronpedia

    INDEX
    Explanations

    references to significant changes or alterations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setCancelable
    -0.38
    Portale
    -0.38
     непо
    -0.37
    IANA
    -0.37
    BagConstraints
    -0.36
     psycho
    -0.36
     Fav
    -0.35
    SetFont
    -0.35
     burglar
    -0.35
     aer
    -0.34
    POSITIVE LOGITS
     change
    1.55
     changement
    1.41
     mudança
    1.37
    change
    1.34
     Veränderung
    1.23
     perubahan
    1.23
     cambio
    1.21
     changes
    1.20
     increase
    1.17
     Change
    1.17
    Act Density 0.333%

    No Known Activations