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

    Neuronpedia

    INDEX
    Explanations

    the presence of formatted mathematical expressions or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reich
    -0.15
    eneg
    -0.14
     AUTHORS
    -0.14
     Payne
    -0.14
     Raj
    -0.14
    ее
    -0.14
     cohorts
    -0.14
    opoulos
    -0.13
    652
    -0.13
    éd
    -0.13
    POSITIVE LOGITS
    otte
    0.16
    anka
    0.15
    late
    0.15
    ssf
    0.15
    hsi
    0.14
    InSection
    0.14
    skou
    0.14
    rang
    0.14
    adro
    0.14
    ấn
    0.14
    Act Density 0.004%

    No Known Activations