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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assessments of value or worth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGE
    -0.19
    ETHOD
    -0.15
    NCY
    -0.14
    Presence
    -0.14
    Æ°Æ¡ng
    -0.14
    .scalablytyped
    -0.14
    _macros
    -0.14
    оби
    -0.14
    meric
    -0.14
    _billing
    -0.14
    POSITIVE LOGITS
    ing
    0.17
     wol
    0.15
    344
    0.15
     Gardner
    0.15
     Wol
    0.14
    oulos
    0.14
     nearest
    0.14
    udo
    0.14
    aji
    0.14
     sentence
    0.14
    Act Density 0.003%

    No Known Activations