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

    Neuronpedia

    INDEX
    Explanations

    variations in situations and their impacts over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    олеÑĤ
    -0.16
    ubb
    -0.15
     Junk
    -0.15
    uesta
    -0.14
    igo
    -0.14
     to
    -0.14
    endor
    -0.14
    UILT
    -0.14
     pert
    -0.14
    inces
    -0.13
    POSITIVE LOGITS
    exus
    0.16
    atics
    0.16
    borne
    0.15
    воÑİ
    0.15
    voie
    0.14
    oro
    0.13
    ilibrium
    0.13
    elves
    0.13
    оÑıн
    0.13
    vel
    0.13
    Act Density 0.107%

    No Known Activations