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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EncodingException
    -0.15
    ilter
    -0.14
     (č↵
    -0.14
    akest
    -0.14
    enti
    -0.14
    thur
    -0.14
    vrier
    -0.14
    ocator
    -0.14
    igung
    -0.13
    ži
    -0.13
    POSITIVE LOGITS
    kins
    0.13
     Rooney
    0.13
     Orig
    0.13
    omp
    0.13
    nen
    0.13
    xt
    0.13
     quarters
    0.13
    es
    0.13
    VP
    0.12
    IBC
    0.12
    Act Density 0.027%

    No Known Activations