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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "In" and other related prepositions within academic citations or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äº
    -0.16
    å¿į
    -0.16
    æĭ©
    -0.15
    achat
    -0.14
    unu
    -0.14
    ế
    -0.14
    etheless
    -0.13
    imi
    -0.13
    \Mapping
    -0.13
    ùng
    -0.13
    POSITIVE LOGITS
     journal
    0.17
    rix
    0.17
    raž
    0.16
    izio
    0.16
    yx
    0.15
    APE
    0.14
    gers
    0.14
    nbr
    0.14
    ivalent
    0.14
    Neutral
    0.14
    Act Density 0.002%

    No Known Activations