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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "More," indicating a focus on additional content or related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iac
    -0.17
    oms
    -0.16
    alf
    -0.15
    पन
    -0.15
    quir
    -0.15
    że
    -0.14
    för
    -0.14
     Bale
    -0.14
    QUI
    -0.14
    ients
    -0.13
    POSITIVE LOGITS
     from
    0.18
    æĿ¥èĩª
    0.16
     info
    0.15
    ttl
    0.15
    iras
    0.15
    au
    0.15
     information
    0.15
     importantly
    0.14
     Tail
    0.14
    aria
    0.14
    Act Density 0.017%

    No Known Activations