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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elez
    -0.17
    usk
    -0.16
    flare
    -0.16
    baru
    -0.15
    ummy
    -0.15
     bounce
    -0.14
    iliz
    -0.14
    facet
    -0.14
    nard
    -0.14
    ahoo
    -0.14
    POSITIVE LOGITS
     terminal
    0.26
     Terminal
    0.23
    Terminal
    0.21
    (ans
    0.20
    terminal
    0.20
     Fore
    0.20
     terminals
    0.20
     Term
    0.19
     ANSI
    0.19
    dim
    0.19
    Act Density 0.013%

    No Known Activations