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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases that imply additional information or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpr
    -0.15
    еÑģа
    -0.13
     rat
    -0.13
    rap
    -0.13
    mah
    -0.13
     sack
    -0.13
    onic
    -0.13
    ensen
    -0.13
    319
    -0.13
    mic
    -0.13
    POSITIVE LOGITS
    unifu
    0.17
    átek
    0.16
    assy
    0.16
    ubar
    0.15
    enery
    0.15
    rious
    0.15
     Thornton
    0.15
    ACITY
    0.14
    :invoke
    0.14
    -ci
    0.14
    Act Density 0.086%

    No Known Activations