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

    Neuronpedia

    INDEX
    Explanations

    references to items that are suspended or attached in a hanging manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tober
    -0.20
    ÅĽci
    -0.17
    MEA
    -0.16
    adera
    -0.15
    immel
    -0.15
    ngör
    -0.15
    orrent
    -0.15
    vise
    -0.15
    ello
    -0.15
    igor
    -0.15
    POSITIVE LOGITS
    éĶĢ
    0.16
     Nev
    0.15
    abis
    0.15
     Paladin
    0.14
    -opacity
    0.14
     roadside
    0.14
    ÑĢд
    0.14
    atta
    0.14
    _self
    0.14
    ucht
    0.14
    Act Density 0.004%

    No Known Activations