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

    Neuronpedia

    INDEX
    Explanations

    references to influencers or content creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.18
    BT
    -0.16
     BT
    -0.16
     bel
    -0.16
     t
    -0.15
     bt
    -0.15
     Andrews
    -0.15
     Peter
    -0.15
    ,
    -0.15
     early
    -0.15
    POSITIVE LOGITS
    meer
    0.18
    edd
    0.15
    asma
    0.15
    Ð¡Ðł
    0.15
    Æ¡i
    0.15
    obb
    0.15
    iê
    0.15
    askell
    0.15
    ritel
    0.14
    .useState
    0.14
    Act Density 0.635%

    No Known Activations