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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and comparative phrases related to similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erable
    -0.21
    tember
    -0.15
    holm
    -0.15
    esktop
    -0.15
    ³
    -0.15
    ponible
    -0.15
     詳細
    -0.14
     itemprop
    -0.14
    rior
    -0.14
    ibold
    -0.14
    POSITIVE LOGITS
    ode
    0.16
    ieee
    0.14
    TED
    0.14
    ynch
    0.14
    (UInt
    0.13
    oci
    0.13
    ̣
    0.13
    DF
    0.13
    itch
    0.13
    ridge
    0.13
    Act Density 0.034%

    No Known Activations