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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "thing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onda
    -0.17
    RTOS
    -0.15
    acket
    -0.15
    atak
    -0.14
    mgr
    -0.14
    fter
    -0.14
     Allison
    -0.14
    onec
    -0.14
    munition
    -0.14
    inson
    -0.13
    POSITIVE LOGITS
     ============================================================================↵
    0.16
    Å¡ku
    0.16
    Boundary
    0.15
    roker
    0.14
    çĴ
    0.14
    iyi
    0.14
     ----------------------------------------------------------------------------↵
    0.14
     sor
    0.14
    anford
    0.14
    .synthetic
    0.13
    Act Density 0.014%

    No Known Activations