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

    Neuronpedia

    INDEX
    Explanations

    phrases related to definitive action or influence

    oai_token-act-pair · gpt-3.5-turbo

    roots or stems of words related to actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     characteristic
    -0.73
     marks
    -0.68
     moments
    -0.66
     wont
    -0.65
    quickShipAvailable
    -0.64
     Waiting
    -0.64
    76561
    -0.62
     Amph
    -0.61
     Sunshine
    -0.61
    DragonMagazine
    -0.60
    POSITIVE LOGITS
    ulate
    1.41
    ize
    1.37
    ify
    1.37
    itate
    1.34
    imize
    1.34
    igrate
    1.33
    rouse
    1.26
    uate
    1.26
    activate
    1.24
    pose
    1.22
    Act Density 0.326%

    No Known Activations