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

    Neuronpedia

    INDEX
    Explanations

    strings and format specifiers commonly used in programming or templating languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omik
    -0.19
    eniz
    -0.16
    ouver
    -0.15
     promot
    -0.14
     traps
    -0.14
    ektor
    -0.13
     Lamp
    -0.13
    ÐĶÐļ
    -0.13
    éģĵ
    -0.13
     äºij
    -0.13
    POSITIVE LOGITS
    479
    0.19
    flater
    0.15
    riott
    0.15
    ιÏİ
    0.15
    refs
    0.15
    elves
    0.14
    .dm
    0.14
    gebn
    0.14
     ngh
    0.14
    inating
    0.14
    Act Density 0.011%

    No Known Activations