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

    Neuronpedia

    INDEX
    Explanations

    words or abbreviations denoting organizations or significant titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ен
    -0.19
    ett
    -0.19
    uh
    -0.18
    oir
    -0.18
    r
    -0.17
    rak
    -0.17
    öy
    -0.17
    uy
    -0.16
    ui
    -0.16
    rig
    -0.15
    POSITIVE LOGITS
    hee
    0.17
    adget
    0.17
    av
    0.17
    ilded
    0.17
    azing
    0.17
    ATE
    0.16
    oni
    0.15
    ird
    0.15
    /MPL
    0.15
    arter
    0.15
    Act Density 0.210%

    No Known Activations