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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or inequalities involving variables and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.60
    -0.52
    wanan
    -0.50
     Control
    -0.49
     Mar
    -0.48
     https
    -0.46
    тров
    -0.46
     vide
    -0.45
     Pen
    -0.45
     N
    -0.45
    POSITIVE LOGITS
     Monfieur
    0.84
    msub
    0.80
     Efq
    0.79
    bootstrapcdn
    0.78
     houſe
    0.76
    ſelf
    0.75
     ―――――
    0.73
     Theſe
    0.73
    ſelves
    0.72
     iſt
    0.71
    Act Density 0.914%

    No Known Activations