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

    Neuronpedia

    INDEX
    Explanations

    phrases that express comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unpl
    -0.15
    yst
    -0.15
    orem
    -0.14
    orf
    -0.14
    ron
    -0.14
    ik
    -0.14
    inen
    -0.13
    abay
    -0.13
     exactly
    -0.13
    hart
    -0.13
    POSITIVE LOGITS
    other
    0.18
     others
    0.17
     other
    0.16
     Mig
    0.16
    oire
    0.16
    others
    0.15
    ãĥ³ãĤ¬
    0.15
    lage
    0.14
    quelle
    0.14
    ä»ĸãģ®
    0.14
    Act Density 0.031%

    No Known Activations