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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "like" and its associations with descriptions or appearances

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

    words connected_like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     země
    -0.59
     consag
    -0.52
     absolutamente
    -0.52
     Geheimnis
    -0.52
     negociación
    -0.51
     TAMBIÉN
    -0.51
    genodigd
    -0.50
     própri
    -0.50
     kří
    -0.50
     rahasia
    -0.50
    POSITIVE LOGITS
    like
    0.88
    Like
    0.65
    LIKE
    0.63
    liken
    0.59
     Like
    0.55
     LIKE
    0.53
    zerű
    0.52
     like
    0.52
    alike
    0.52
    similar
    0.51
    Act Density 0.019%

    No Known Activations