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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expressions and their effects on characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.86
    apimachinery
    -0.86
     itſelf
    -0.83
    -0.83
     tartalomajánló
    -0.83
    ſelf
    -0.83
     occaf
    -0.83
     getItemCount
    -0.81
    ="@+
    -0.81
     Majefty
    -0.79
    POSITIVE LOGITS
     enquanto
    0.91
     while
    0.91
     when
    0.79
    while
    0.79
     mientras
    0.78
     Enquanto
    0.71
    when
    0.68
    Mientras
    0.68
     mentre
    0.64
    WHILE
    0.62
    Act Density 0.197%

    No Known Activations