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

    Neuronpedia

    INDEX
    Explanations

    comment or documentation blocks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emies
    -0.15
    imenti
    -0.15
    agi
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    actable
    -0.14
    sat
    -0.14
    /***/
    -0.14
     Gabriel
    -0.14
    ÏģÏİ
    -0.14
    ework
    -0.14
    POSITIVE LOGITS
     |--------------------------------------------------------------------------↵
    0.23
     *
    0.21
    |--------------------------------------------------------------------------↵
    0.21
     *↵
    0.16
    eward
    0.15
     fever
    0.15
    ijk
    0.15
     heads
    0.14
    lier
    0.14
     Nav
    0.14
    Act Density 0.028%

    No Known Activations