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

    Neuronpedia

    INDEX
    Explanations

    the significance of concepts or statements related to importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.84
     Roskov
    -0.79
    RunWith
    -0.79
     IEnumerator
    -0.68
     autorytatywna
    -0.66
    jooq
    -0.64
     Référence
    -0.63
     springfox
    -0.61
    Lähteet
    -0.61
    Autoritní
    -0.60
    POSITIVE LOGITS
     important
    4.47
    important
    4.00
     Important
    3.81
    Important
    3.62
     IMPORTANT
    3.09
     importante
    3.05
     importantes
    2.86
     importanti
    2.84
     importants
    2.83
     penting
    2.79
    Act Density 0.133%

    No Known Activations