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

    Neuronpedia

    INDEX
    Explanations

    references to reading and continuation prompts within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ters
    -0.15
     talent
    -0.15
    bst
    -0.14
     jur
    -0.14
    Âłmi
    -0.14
    lope
    -0.13
    tal
    -0.13
     PyErr
    -0.13
     Hooks
    -0.13
     offsets
    -0.13
    POSITIVE LOGITS
    ÑĸÑĶ
    0.15
    ãĥ³ãĥĩ
    0.15
    \OptionsResolver
    0.14
    ohl
    0.14
    hots
    0.14
    ãĥ³ãĤ°
    0.14
    ï¸
    0.14
    raÄį
    0.13
    ysi
    0.13
     Singleton
    0.13
    Act Density 0.008%

    No Known Activations