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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions or connectors in complex phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rez
    -0.18
    sdale
    -0.17
    eyse
    -0.16
    ÙıÙĨ
    -0.15
     âĵĺ
    -0.15
    achable
    -0.15
    bill
    -0.15
    ÑĮко
    -0.14
    addOn
    -0.14
    abcdefghijkl
    -0.14
    POSITIVE LOGITS
    /or
    0.17
    iceps
    0.16
     Brook
    0.15
     aqu
    0.15
     Beam
    0.15
    Ñģком
    0.14
    ainter
    0.14
    /OR
    0.14
     hack
    0.14
     twin
    0.13
    Act Density 0.126%

    No Known Activations