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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or liking

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

    "like" or "likes" followed by infinitives or objects

    np_acts-logits-general · gemini-2.0-flash

    like to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getDoctrine
    -0.64
    ات
    -0.61
    se
    -0.58
    ResumeLayout
    -0.56
    arXiv
    -0.56
    pub
    -0.55
     quanto
    -0.55
    devServer
    -0.55
     mencapai
    -0.53
    dymyr
    -0.53
    POSITIVE LOGITS
    liest
    0.84
     EconPapers
    0.82
    +#+#
    0.74
    lihood
    0.72
    évaluateur
    0.67
    postIndex
    0.67
    dislike
    0.65
     Мексичка
    0.65
     ivelany
    0.64
    👍👍
    0.64
    Act Density 0.050%

    No Known Activations