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

    Neuronpedia

    INDEX
    Explanations

    the word "conduct" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dreamer
    -0.75
     Rebellion
    -0.72
    WebVitals
    -0.71
    SizeF
    -0.70
    KeyListener
    -0.69
     VES
    -0.69
     serializer
    -0.68
    zepine
    -0.68
     Tessa
    -0.67
     Keyes
    -0.67
    POSITIVE LOGITS
     conduct
    2.76
    Conduct
    2.72
     conducted
    2.71
     Conduct
    2.69
     CONDUCT
    2.58
     conducts
    2.54
    conduct
    2.50
    conducted
    2.44
     conducting
    2.37
     Conducted
    2.28
    Act Density 0.078%

    No Known Activations