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

    Neuronpedia

    INDEX
    Explanations

    themes related to community concerns and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipur
    -0.18
    ãĤ
    -0.17
    جة
    -0.15
    hta
    -0.15
    POCH
    -0.14
     nonce
    -0.14
    asn
    -0.14
    avana
    -0.14
    esch
    -0.14
    onda
    -0.13
    POSITIVE LOGITS
    odash
    0.15
     Benson
    0.15
    2
    0.14
     duo
    0.14
    lero
    0.14
    Expose
    0.13
    wu
    0.13
    eczy
    0.13
     Manga
    0.13
     Îļά
    0.13
    Act Density 0.526%

    No Known Activations