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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ģ
    -0.16
    ãĥĥãĥģ
    -0.15
    .structure
    -0.14
    ochen
    -0.14
     Bil
    -0.14
    angel
    -0.14
    tails
    -0.14
    ksi
    -0.14
    raphics
    -0.13
     doub
    -0.13
    POSITIVE LOGITS
     favorite
    0.23
     favorites
    0.23
     favourite
    0.21
     favourites
    0.21
     understanding
    0.19
     Favorite
    0.19
     picks
    0.19
    favorite
    0.18
     pick
    0.18
    åį°
    0.17
    Act Density 0.135%

    No Known Activations