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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words indicating continuation or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anken
    -0.14
     ebenfalls
    -0.13
    изнеÑģ
    -0.13
     sondern
    -0.12
    atti
    -0.12
    iken
    -0.12
    NaN
    -0.12
     Otherwise
    -0.12
    unan
    -0.12
    ivol
    -0.12
    POSITIVE LOGITS
     even
    1.30
    even
    1.13
     EVEN
    0.98
     Even
    0.97
     sogar
    0.95
    Even
    0.94
     даже
    0.93
    çĶļèĩ³
    0.90
     навÑĸÑĤÑĮ
    0.81
     nawet
    0.79
    Act Density 0.519%

    No Known Activations