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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    246
    -0.16
     Trot
    -0.15
    ongs
    -0.15
    ilim
    -0.14
    arih
    -0.14
    illon
    -0.14
    keit
    -0.13
    تع
    -0.13
    aston
    -0.13
    Parcel
    -0.13
    POSITIVE LOGITS
     Antar
    0.17
    аÑĢÑĩ
    0.16
    é¼»
    0.16
    erta
    0.15
    czy
    0.15
    ress
    0.14
     Erf
    0.13
    ãĥ¼ãĥ«
    0.13
    Arrow
    0.13
    owell
    0.13
    Act Density 0.340%

    No Known Activations