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

    Neuronpedia

    INDEX
    Explanations

    comparative measurements regarding various thresholds and limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendriers
    -0.52
    TintMode
    -0.50
    Искәрмәләр
    -0.50
    httphttps
    -0.44
    consulté
    -0.44
    gave
    -0.41
     Stil
    -0.41
     et
    -0.41
     Drapeau
    -0.40
    chelles
    -0.40
    POSITIVE LOGITS
     threshold
    0.82
     varandra
    0.69
     thresholds
    0.69
     Anſ
    0.69
     Monfieur
    0.69
     Houſe
    0.68
     thresh
    0.68
     Efq
    0.67
     raisonnable
    0.66
     themſelves
    0.66
    Act Density 0.607%

    No Known Activations