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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and other linking words that connect ideas or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieres
    -0.16
    ocale
    -0.16
    marca
    -0.15
    arine
    -0.15
    raries
    -0.15
    bard
    -0.14
    ugins
    -0.14
    exus
    -0.14
    ariat
    -0.14
    ucene
    -0.13
    POSITIVE LOGITS
    ily
    0.14
     Apt
    0.14
    ji
    0.13
     Fraction
    0.13
     considering
    0.13
    aver
    0.13
    леÑĩ
    0.13
    _fraction
    0.13
    sted
    0.13
    eli
    0.13
    Act Density 0.316%

    No Known Activations