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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to trans-dimensional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spiel
    -0.18
    inson
    -0.17
    ÅĽmy
    -0.16
    tsy
    -0.15
    .smtp
    -0.15
    ong
    -0.15
    ows
    -0.15
    _PARTITION
    -0.15
    strap
    -0.14
    ãģ¨ãģį
    -0.14
    POSITIVE LOGITS
    /trans
    0.27
    aksi
    0.21
    -trans
    0.18
    sexual
    0.17
    nock
    0.17
    .trans
    0.17
    (trans
    0.16
    rail
    0.16
    al
    0.15
    çŀ¬
    0.15
    Act Density 0.062%

    No Known Activations