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

    Neuronpedia

    INDEX
    Explanations

    words related to advancements, progress, advice, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to advancements and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SIZE
    -0.79
    cules
    -0.65
    mates
    -0.65
    ISM
    -0.64
    LOAD
    -0.63
    morph
    -0.62
    gob
    -0.62
    SHARE
    -0.62
    lines
    -0.62
    mie
    -0.61
    POSITIVE LOGITS
    anced
    1.21
    ancing
    1.19
    ocate
    1.18
    ances
    1.05
    ices
    1.02
    isance
    0.93
    ising
    0.93
    ance
    0.92
    enture
    0.92
    ises
    0.90
    Act Density 0.010%

    No Known Activations