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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and their contextual variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.58
    very
    -0.50
    this
    -0.50
     sapp
    -0.49
     Drapeau
    -0.49
    Fin
    -0.46
    ãng
    -0.45
     Abp
    -0.45
    Hub
    -0.45
     Ory
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.98
    qrstuvwxyz
    0.93
     <=",
    0.70
    
    0.69
    InitVars
    0.64
     tombé
    0.63
     vertes
    0.63
    التالي
    0.63
     vapeur
    0.63
     automatiques
    0.62
    Act Density 0.482%

    No Known Activations