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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     οποία
    -0.78
    ों
    -0.74
     Ancona
    -0.73
    cini
    -0.72
    ES
    -0.72
    es
    -0.71
    ์ตูน
    -0.71
     Mahmoud
    -0.70
    ity
    -0.68
     PopupWindow
    -0.68
    POSITIVE LOGITS
     like
    2.04
     LIKE
    1.99
     Like
    1.92
    Like
    1.88
    like
    1.75
    LIKE
    1.72
    Likes
    1.20
    likes
    1.19
     likes
    1.19
     Likes
    1.19
    Act Density 0.141%

    No Known Activations