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

    Neuronpedia

    INDEX
    Explanations

    concepts related to unity and connection among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WillAppear
    -0.64
     Yourself
    -0.60
    DoubleQuotes
    -0.60
    (&:
    -0.58
     SqlConnection
    -0.55
    UrlResolution
    -0.52
     yourself
    -0.52
     Myself
    -0.52
     himself
    -0.52
     Himself
    -0.52
    POSITIVE LOGITS
     us
    0.80
     me
    0.68
     them
    0.66
     our
    0.63
     you
    0.62
    帖最后由
    0.59
    AddTagHelper
    0.59
     him
    0.57
     jinak
    0.54
     incomplète
    0.54
    Act Density 0.489%

    No Known Activations