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

    Neuronpedia

    INDEX
    Explanations

    words related to engagement and connection in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    хьтан
    -1.03
     AssemblyTitle
    -1.00
    WebServlet
    -0.96
     continúas
    -0.94
     AssemblyCompany
    -0.93
    OGND
    -0.93
     HasFactory
    -0.92
    AndEndTag
    -0.92
     мәкал
    -0.92
     Италијани
    -0.91
    POSITIVE LOGITS
    '
    0.61
    ’
    0.52
    .
    0.51
    <eos>
    0.50
    ur
    0.47
    de
    0.46
    lo
    0.44
    da
    0.44
    בוצ
    0.43
    ss
    0.43
    Act Density 0.321%

    No Known Activations