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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate specific age ranges or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xor
    -0.15
    orda
    -0.14
    month
    -0.13
    terr
    -0.13
    ILLA
    -0.13
    ÑģÑĭл
    -0.13
    UNET
    -0.13
    ernals
    -0.13
    immer
    -0.12
    another
    -0.12
    POSITIVE LOGITS
     ages
    0.32
     roughly
    0.27
     Ages
    0.26
     from
    0.26
     ranges
    0.25
     birth
    0.24
     ranging
    0.24
     approximately
    0.23
     between
    0.23
    rough
    0.23
    Act Density 0.082%

    No Known Activations