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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completion or the presence of certain elements in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionTypes
    -0.18
     ActionTypes
    -0.16
    ounty
    -0.15
    .kr
    -0.14
     Impossible
    -0.14
    zzo
    -0.14
     âĹĦ
    -0.14
     immediate
    -0.14
    çĿ
    -0.14
    tae
    -0.14
    POSITIVE LOGITS
    hausen
    0.16
    führt
    0.15
    endor
    0.15
    ıyla
    0.14
    ansk
    0.14
    ery
    0.14
    apot
    0.14
    Vir
    0.14
     accompanying
    0.14
     Moon
    0.14
    Act Density 0.021%

    No Known Activations