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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental research and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.18
    pagen
    -0.18
    nap
    -0.15
    uracy
    -0.15
    achi
    -0.15
    elper
    -0.15
    VERTISE
    -0.15
    enticate
    -0.15
    ward
    -0.15
    heid
    -0.15
    POSITIVE LOGITS
    ally
    0.21
    室
    0.17
    ALLY
    0.17
    ative
    0.16
    ogue
    0.16
    .UnitTesting
    0.15
    stations
    0.15
    allback
    0.15
    elling
    0.15
    zzo
    0.15
    Act Density 0.016%

    No Known Activations