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

    Neuronpedia

    INDEX
    Explanations

    instances of contrasting conjunctions or phrases indicating qualification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     although
    -0.14
    /wiki
    -0.14
    assy
    -0.14
    elah
    -0.14
    although
    -0.14
    ienes
    -0.13
    526
    -0.13
    artial
    -0.13
    utan
    -0.13
    ango
    -0.13
    POSITIVE LOGITS
    DK
    0.15
    alles
    0.14
    nik
    0.14
    ű
    0.14
    lus
    0.14
     certainly
    0.13
    vro
    0.13
    vant
    0.13
     Dek
    0.13
    ãĤ·ãĥ£ãĥ«
    0.13
    Act Density 0.136%

    No Known Activations