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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal identity and social interactions

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

    was followed by adjective or participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cresce
    -0.25
     near
    -0.25
    にあります
    -0.24
     ting
    -0.24
    走到
    -0.24
     analyzed
    -0.23
    走在
    -0.22
    substack
    -0.22
     الأم
    -0.22
    pfen
    -0.21
    POSITIVE LOGITS
     EconPapers
    0.86
     snippetHide
    0.82
     שוליים
    0.77
     autorytatywna
    0.76
    ViewFeatures
    0.74
    <unused79>
    0.73
    <unused14>
    0.73
    <unused28>
    0.73
    <unused8>
    0.73
    [@BOS@]
    0.73
    Act Density 0.066%

    No Known Activations