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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly those with expertise or notable contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.15
    ĶåĽŀ
    -0.15
     Brooke
    -0.15
    ypress
    -0.14
    72
    -0.14
     -↵↵
    -0.14
    ÑģоÑĢ
    -0.14
    çĪ·
    -0.14
    HA
    -0.14
    alta
    -0.14
    POSITIVE LOGITS
    renc
    0.17
     above
    0.17
     Natur
    0.16
    odate
    0.16
     natur
    0.15
    ã
    0.15
    anmar
    0.15
    alin
    0.14
    nik
    0.14
    اÙħØ©
    0.14
    Act Density 0.005%

    No Known Activations