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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or liking towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    likes and dislikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BSE
    -0.46
     TCU
    -0.46
     Barriers
    -0.45
    ことはありません
    -0.45
     SOA
    -0.44
     EDR
    -0.44
     Osw
    -0.43
     FMC
    -0.43
     MSW
    -0.42
     Crucible
    -0.42
    POSITIVE LOGITS
    Liked
    0.80
     liked
    0.79
    liked
    0.76
     Liked
    0.75
    Dislikes
    0.73
    dislike
    0.72
    Likes
    0.68
     LIKE
    0.68
     likes
    0.66
    likes
    0.65
    Act Density 0.014%

    No Known Activations