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

    Neuronpedia

    INDEX
    Explanations

    language related to intentions, plans, or motives

    oai_token-act-pair · gpt-3.5-turbo

    references to intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rooms
    -0.82
    ded
    -0.78
    thumbnails
    -0.73
    GS
    -0.71
    upon
    -0.69
    room
    -0.69
    sen
    -0.67
    Lear
    -0.66
    enegger
    -0.66
    Interstitial
    -0.65
    POSITIVE LOGITS
     intentions
    0.97
    omething
    0.84
    pring
    0.77
     motivations
    0.75
    uggest
    0.75
     behavi
    0.73
    afety
    0.72
    poons
    0.72
     intent
    0.71
    cape
    0.71
    Act Density 0.029%

    No Known Activations