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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate an action or prompt for change

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

    phrases indicating the passage of time or the need for action

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Sold
    -0.77
    person
    -0.69
    Wallet
    -0.62
    listed
    -0.61
    Person
    -0.61
    rn
    -0.60
    volent
    -0.60
    ById
    -0.59
    RF
    -0.59
    Aust
    -0.59
    POSITIVE LOGITS
     revisit
    1.26
     celebrate
    1.16
     retire
    1.05
     introduce
    0.95
     settle
    0.95
     reconsider
    0.95
     revise
    0.94
     discuss
    0.93
     rethink
    0.93
     assemble
    0.92
    Act Density 0.054%

    No Known Activations