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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or situations starting or initiating

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "opened."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grade
    -0.68
    orum
    -0.67
    âĨij
    -0.66
    rior
    -0.64
    tz
    -0.63
     Cyborg
    -0.62
    hov
    -0.61
    CTV
    -0.60
    ivable
    -0.60
    iable
    -0.60
    POSITIVE LOGITS
     doors
    0.88
     Doors
    0.84
     up
    0.83
    ource
    0.78
    lique
    0.76
     wounds
    0.72
     curtains
    0.72
    ococ
    0.72
    bucks
    0.72
    UP
    0.71
    Act Density 0.040%

    No Known Activations