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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey appreciation or positive sentiments about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ƚ
    -0.54
    -0.53
    InSection
    -0.50
    WebServlet
    -0.49
    fromnode
    -0.48
     незавершена
    -0.47
    UserScript
    -0.47
     AssemblyCulture
    -0.47
    parsedMessage
    -0.47
    VolleyError
    -0.46
    POSITIVE LOGITS
    zeß
    0.41
     Ternyata
    0.40
    èdia
    0.37
    bestos
    0.34
    liği
    0.34
     eben
    0.34
     fascinating
    0.33
     parezca
    0.33
    apprendre
    0.33
     BoxDecoration
    0.33
    Act Density 0.013%

    No Known Activations