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

    Neuronpedia

    INDEX
    Explanations

    horizontal separators or dividers in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.75
     Inſ
    -0.75
     pleaſure
    -0.75
     Perſ
    -0.65
     Monfieur
    -0.65
     feroit
    -0.64
     greateſt
    -0.64
     queſta
    -0.63
     Houſe
    -0.62
     Anſ
    -0.61
    POSITIVE LOGITS
    ---
    1.40
     ---
    1.10
    ***
    1.04
    ---
    0.98
    ___
    0.89
    //---
    0.79
     ***
    0.76
    .---
    0.76
     "---
    0.68
    ("---
    0.67
    Act Density 0.219%

    No Known Activations