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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousel
    -0.17
    orie
    -0.15
     either
    -0.14
    over
    -0.14
    inned
    -0.14
    ount
    -0.14
     Severity
    -0.13
    either
    -0.13
    ebra
    -0.13
    orting
    -0.13
    POSITIVE LOGITS
     Bes
    0.15
     totalPages
    0.14
    tere
    0.14
     Orient
    0.14
    urm
    0.14
     orient
    0.14
    vil
    0.14
    oger
    0.14
     note
    0.13
     fakt
    0.13
    Act Density 0.129%

    No Known Activations