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

    Neuronpedia

    INDEX
    Explanations

    expressions of liking or enjoying something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     سكانية
    -0.53
     <<<<<<<<<<<<<<
    -0.50
    脚注の使い方
    -0.48
     TCU
    -0.44
     covert
    -0.44
     travelers
    -0.43
     Purcell
    -0.43
     malpractice
    -0.43
     travellers
    -0.42
    ⎡
    -0.41
    POSITIVE LOGITS
     liked
    1.20
     Liked
    1.13
    Liked
    1.11
    liked
    1.02
     liking
    0.98
     Likes
    0.87
    Likes
    0.86
     likes
    0.86
    likes
    0.79
    Dislikes
    0.78
    Act Density 0.176%

    No Known Activations