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

    Neuronpedia

    INDEX
    Explanations

    words related to social media engagement and personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Britt
    -0.17
    Bond
    -0.15
    adows
    -0.15
    abella
    -0.14
    å±Ĩ
    -0.14
    -equiv
    -0.14
    duino
    -0.14
     Cav
    -0.14
     addCriterion
    -0.14
    jav
    -0.14
    POSITIVE LOGITS
    /Dk
    0.15
    anton
    0.15
     Wonderland
    0.15
    RACT
    0.14
     Perm
    0.14
     Äijo
    0.14
     FLT
    0.14
     Spl
    0.14
    enumer
    0.13
    é¤
    0.13
    Act Density 0.000%

    No Known Activations