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

    Neuronpedia

    INDEX
    Explanations

    patterns in structured data or programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maul
    -0.16
    utdown
    -0.15
    IAS
    -0.15
     Abel
    -0.15
    enga
    -0.15
     Qual
    -0.14
    èĤ¥
    -0.14
    spÄĽ
    -0.14
     Marion
    -0.14
    rone
    -0.14
    POSITIVE LOGITS
    íĹĮ
    0.15
    jerne
    0.14
    usercontent
    0.14
     Journalism
    0.14
    rve
    0.13
    asti
    0.13
    andum
    0.13
    afen
    0.13
     Benedict
    0.13
    .metamodel
    0.13
    Act Density 0.005%

    No Known Activations