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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ots
    -0.16
    noop
    -0.16
    OTS
    -0.14
    Ĥ¨
    -0.14
    OOK
    -0.13
     competitive
    -0.13
    ccione
    -0.13
     Guth
    -0.13
    esen
    -0.13
    STE
    -0.13
    POSITIVE LOGITS
    för
    0.16
    warm
    0.15
     rag
    0.14
     glac
    0.14
     vir
    0.13
    olit
    0.13
    hend
    0.13
    lamaz
    0.13
     McKenzie
    0.13
    emd
    0.13
    Act Density 0.005%

    No Known Activations