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

    Neuronpedia

    INDEX
    Explanations

    common prepositions and conjunctions indicating relationships between phrases and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adder
    -0.18
    adders
    -0.16
    opot
    -0.16
    isman
    -0.15
    dom
    -0.15
    edar
    -0.15
    adas
    -0.15
    orig
    -0.14
     Domin
    -0.14
    alamat
    -0.14
    POSITIVE LOGITS
    /cms
    0.17
    omi
    0.17
    424
    0.15
    voje
    0.15
     дво
    0.15
    accom
    0.15
    nier
    0.14
    413
    0.14
    426
    0.14
     اÙĦعاÙĦÙħ
    0.14
    Act Density 0.001%

    No Known Activations