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

    Neuronpedia

    INDEX
    Explanations

    terms related to openness or being open to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "open."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.74
    iage
    -0.74
    doms
    -0.69
    grade
    -0.66
    CTV
    -0.66
    ILL
    -0.65
    minster
    -0.65
    ********************************
    -0.64
    ORGE
    -0.63
    ioxide
    -0.63
    POSITIVE LOGITS
    office
    0.83
    open
    0.79
     minded
    0.78
     spaces
    0.78
     wounds
    0.76
     parentheses
    0.71
     open
    0.71
     scrimmage
    0.70
    ahead
    0.69
    lique
    0.69
    Act Density 0.038%

    No Known Activations