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

    Neuronpedia

    INDEX
    Explanations

    references to animals in a contextual or metaphorical way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лÑİÑĩаеÑĤÑģÑı
    -0.16
    was
    -0.15
    arlo
    -0.15
    íķĺëĭ¤
    -0.14
     должен
    -0.14
    sta
    -0.14
     Spear
    -0.14
    uhe
    -0.14
    ph
    -0.14
    asta
    -0.14
    POSITIVE LOGITS
     são
    0.36
     estão
    0.32
     podem
    0.31
     foram
    0.28
     sao
    0.28
     tin
    0.26
     têm
    0.25
     serão
    0.24
     were
    0.23
     are
    0.22
    Act Density 0.008%

    No Known Activations