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

    Neuronpedia

    INDEX
    Explanations

    instances of assignment or declaration statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avar
    -0.17
    ãĤħ
    -0.15
    arer
    -0.15
    stalk
    -0.15
    ritt
    -0.14
    ynth
    -0.14
    ingle
    -0.14
    µľ
    -0.14
     dor
    -0.14
    ceptar
    -0.14
    POSITIVE LOGITS
    VILLE
    0.15
    _ABI
    0.14
    ushima
    0.14
    pecific
    0.14
     PROCUREMENT
    0.14
    sen
    0.14
    ebi
    0.14
    gas
    0.14
    sd
    0.14
    enties
    0.14
    Act Density 0.002%

    No Known Activations