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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĤad
    -0.16
    _suspend
    -0.15
    ouch
    -0.14
    lsen
    -0.14
    OUCH
    -0.14
    verse
    -0.14
    _DISPATCH
    -0.14
    edin
    -0.14
    ourse
    -0.13
    ÃŃcul
    -0.13
    POSITIVE LOGITS
     selection
    0.21
     choices
    0.21
     selections
    0.20
     choice
    0.20
    choice
    0.19
     decision
    0.19
    _Selection
    0.18
    Choice
    0.18
     selecting
    0.18
     Selection
    0.18
    Act Density 0.177%

    No Known Activations