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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numerical values and specific syntactical structures in code or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esco
    -0.15
    im
    -0.15
     mes
    -0.14
    .vm
    -0.14
    in
    -0.14
    ynes
    -0.13
    añ
    -0.13
    deaux
    -0.13
    imers
    -0.13
    261
    -0.13
    POSITIVE LOGITS
    nist
    0.16
    dash
    0.16
    azen
    0.15
    ubi
    0.14
     dict
    0.14
    iba
    0.14
    ichten
    0.14
    agma
    0.14
     Dict
    0.14
    xon
    0.14
    Act Density 0.032%

    No Known Activations