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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate decision-making or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.52
     caminhão
    -0.46
     ônibus
    -0.46
     Rasmussen
    -0.44
     marrom
    -0.44
    Basketball
    -0.43
     Rtl
    -0.42
    ględ
    -0.42
     tunnels
    -0.42
     Basketball
    -0.42
    POSITIVE LOGITS
     choice
    2.13
     Choice
    2.03
    choice
    2.03
    Choice
    2.02
     CHOICE
    1.84
    CHOICE
    1.69
    choices
    1.56
     choices
    1.53
    Choices
    1.48
     choix
    1.44
    Act Density 0.140%

    No Known Activations