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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call or demand for action

    oai_token-act-pair · gpt-3.5-turbo

    calls for action or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    puted
    -0.66
    port
    -0.66
     Madden
    -0.64
    uded
    -0.64
    hack
    -0.64
     Smy
    -0.62
    along
    -0.60
    leon
    -0.60
    semble
    -0.60
    under
    -0.60
    POSITIVE LOGITS
    bidden
    0.85
     abol
    0.84
     stricter
    0.79
     reconsider
    0.77
    psey
    0.76
    gery
    0.75
    geries
    0.73
    nesty
    0.72
    enei
    0.71
     mandatory
    0.70
    Act Density 0.047%

    No Known Activations