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

    Neuronpedia

    INDEX
    Explanations

    academic achievements and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andom
    -0.15
    ochen
    -0.15
    ги
    -0.14
    ine
    -0.14
     Miranda
    -0.14
    oš
    -0.14
    iesz
    -0.14
    coach
    -0.13
    aley
    -0.13
    lund
    -0.13
    POSITIVE LOGITS
     distinction
    0.26
     cum
    0.23
     Dist
    0.22
    Dist
    0.22
    dist
    0.21
     sum
    0.21
    -dist
    0.20
    agna
    0.20
     Cum
    0.20
     magna
    0.19
    Act Density 0.053%

    No Known Activations