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

    Neuronpedia

    INDEX
    Explanations

    elements and symbols related to mathematical notation or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.59
     joaat
    -0.56
    ?}",
    -0.56
    gac
    -0.55
     Waterman
    -0.53
     Seul
    -0.52
    ümüz
    -0.52
    ✭
    -0.51
    стоин
    -0.51
     Ropa
    -0.51
    POSITIVE LOGITS
    bing
    0.72
    BRI
    0.69
     bú
    0.67
     Leber
    0.64
    nesses
    0.64
    bn
    0.62
    buh
    0.62
    bbing
    0.61
     bing
    0.59
    bh
    0.58
    Act Density 0.603%

    No Known Activations