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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating continuity or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sobie
    -0.17
    /licenses
    -0.16
    ả
    -0.15
    anko
    -0.14
    uz
    -0.14
    ino
    -0.14
    tor
    -0.14
     Victim
    -0.13
    便
    -0.13
     excess
    -0.13
    POSITIVE LOGITS
    apur
    0.16
    erland
    0.16
     abroad
    0.15
    asaki
    0.15
    YTE
    0.15
    ponge
    0.15
     наÑĤ
    0.14
    quam
    0.14
    urope
    0.14
    ipur
    0.14
    Act Density 0.418%

    No Known Activations