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

    Neuronpedia

    INDEX
    Explanations

    text fragments indicating contrast or comparison within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.16
    anno
    -0.15
    ally
    -0.15
    ilst
    -0.14
     dolayı
    -0.14
    kara
    -0.14
    reno
    -0.13
    nnen
    -0.13
     ln
    -0.13
    ilo
    -0.13
    POSITIVE LOGITS
    lington
    0.16
    eck
    0.15
    gos
    0.15
     Rosenstein
    0.14
    avec
    0.14
    ãĥ³ãĤº
    0.14
    emble
    0.14
     Meadows
    0.14
    quette
    0.14
    cul
    0.14
    Act Density 0.227%

    No Known Activations