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

    Neuronpedia

    INDEX
    Explanations

    words related to passivity or inactivity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "activity" or "interactivity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dar
    -0.68
     Dollar
    -0.63
     Grand
    -0.62
     veins
    -0.61
    far
    -0.61
     arm
    -0.59
     fucked
    -0.59
     Horse
    -0.58
     brothers
    -0.58
     Bir
    -0.57
    POSITIVE LOGITS
    ivity
    4.75
    ivities
    3.05
    iveness
    2.52
    ivism
    2.18
    ively
    1.88
    ives
    1.61
    ivist
    1.58
    ive
    1.58
    ivation
    1.49
    ativity
    1.41
    Act Density 0.008%

    No Known Activations