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

    Neuronpedia

    INDEX
    Explanations

    references to preferences or comparisons involving "like" or "likes."

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

    the likes of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.53
    embatan
    -0.51
    ctomy
    -0.50
    enderal
    -0.49
     Towels
    -0.49
     Oatmeal
    -0.48
     Potato
    -0.47
     Schot
    -0.47
    setCellValue
    -0.47
    omotor
    -0.47
    POSITIVE LOGITS
     likes
    1.53
    likes
    1.18
     Likes
    1.09
    Likes
    1.06
    like
    0.71
    IKES
    0.68
     LIKE
    0.63
     gosta
    0.60
    Like
    0.59
     liked
    0.59
    Act Density 0.003%

    No Known Activations