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

    Neuronpedia

    INDEX
    Explanations

    initial tokens that indicate the beginning of a document or a noteworthy segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.85
     Shakspeare
    -0.81
     doInBackground
    -0.80
    abetes
    -0.76
     AssemblyTitle
    -0.71
    FundMe
    -0.71
    RenderAtEndOf
    -0.70
    esterday
    -0.69
    ſelf
    -0.69
    ſelves
    -0.69
    POSITIVE LOGITS
     it
    0.58
     they
    0.50
     this
    0.48
     catatan
    0.46
     apostar
    0.45
     vielä
    0.45
     bocca
    0.45
     jegy
    0.45
     tuttavia
    0.44
     pribadi
    0.44
    Act Density 0.337%

    No Known Activations