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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a desire for feedback or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artner
    -0.15
    _PT
    -0.15
    wie
    -0.14
    ocket
    -0.14
    uzzi
    -0.14
     kry
    -0.14
    ROLS
    -0.13
    ÑģÑĮ
    -0.13
     Localization
    -0.13
    ERGY
    -0.13
    POSITIVE LOGITS
    471
    0.17
    611
    0.17
     Vern
    0.16
    379
    0.15
    lem
    0.14
    orre
    0.14
    ila
    0.14
    åŃĹå¹ķ
    0.14
     Ron
    0.14
     any
    0.14
    Act Density 0.033%

    No Known Activations