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

    Neuronpedia

    INDEX
    Explanations

    references to actions starting with the word "opened"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "open" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orum
    -0.67
    rior
    -0.66
    CTV
    -0.65
    grade
    -0.64
    iable
    -0.61
    stood
    -0.60
    âĨij
    -0.59
    ashington
    -0.58
    Bey
    -0.57
     constitu
    -0.56
    POSITIVE LOGITS
     Doors
    0.94
     doors
    0.92
     up
    0.87
     wounds
    0.81
    ource
    0.77
    lique
    0.77
    UP
    0.77
     parentheses
    0.74
    bucks
    0.72
     portals
    0.72
    Act Density 0.042%

    No Known Activations