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

    Neuronpedia

    INDEX
    Explanations

    activations of the pronouns "He," "We," and "my," indicating a focus on personal or collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ķ
    -0.15
    .Unity
    -0.15
    ''''
    -0.13
    ë³´ëĤ´ê¸°
    -0.13
    -REAL
    -0.13
    lož
    -0.13
    ÑģÑĤвоÑĢ
    -0.13
    ODEV
    -0.13
    abi
    -0.13
    redd
    -0.13
    POSITIVE LOGITS
    rtype
    0.14
    unar
    0.13
    ourt
    0.13
    @Web
    0.13
    asic
    0.13
    pedia
    0.12
     consec
    0.12
    CEF
    0.12
     Pradesh
    0.12
    intptr
    0.12
    Act Density 0.463%

    No Known Activations