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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making choices or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "choose" or "choice"

    np_acts-logits-general · gemini-2.0-flash

    choosing from options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.77
     فريبيس
    -0.70
     tuturor
    -0.66
    انيف
    -0.66
     appellants
    -0.65
     "}";
    -0.62
     Dutchman
    -0.61
     forbindelse
    -0.61
     bershka
    -0.60
     picioare
    -0.60
    POSITIVE LOGITS
     Choices
    1.04
     choices
    0.97
     Choice
    0.92
    Choices
    0.90
     chooses
    0.88
     choice
    0.86
    choices
    0.84
     CHOICE
    0.83
     chose
    0.83
     lựa
    0.82
    Act Density 0.119%

    No Known Activations