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

    Neuronpedia

    INDEX
    Explanations

    instances of relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dÆ°Æ¡ng
    -0.16
    zac
    -0.15
    serie
    -0.15
    aal
    -0.15
    mos
    -0.15
    vailability
    -0.15
    bon
    -0.15
    DN
    -0.14
    bjerg
    -0.14
    aar
    -0.14
    POSITIVE LOGITS
     originally
    0.16
     fork
    0.16
    سÙĬ
    0.15
    μβ
    0.14
     drum
    0.14
    hs
    0.14
    uir
    0.14
     sey
    0.14
    endors
    0.14
    opsis
    0.14
    Act Density 0.311%

    No Known Activations