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

    Neuronpedia

    INDEX
    Explanations

    references to personal choices and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peralta
    -0.76
     îna
    -0.74
    Tembelea
    -0.73
     rispar
    -0.73
     appellants
    -0.73
     dumne
    -0.72
    Dammit
    -0.71
     episódios
    -0.71
     παιδιά
    -0.70
    menina
    -0.69
    POSITIVE LOGITS
     Choices
    1.71
     choices
    1.70
     Choice
    1.60
     CHOICE
    1.57
     choice
    1.57
    Choices
    1.50
    choices
    1.46
    Choice
    1.44
    CHOICE
    1.41
    choice
    1.40
    Act Density 0.055%

    No Known Activations