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

    Neuronpedia

    INDEX
    Explanations

    text related to author names and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rada
    -0.16
    ivec
    -0.15
    émon
    -0.14
    ãģ¥
    -0.14
    atk
    -0.14
     rep
    -0.14
    StatusLabel
    -0.14
    egov
    -0.14
    resar
    -0.14
    pmat
    -0.14
    POSITIVE LOGITS
     aktu
    0.14
     Lindsay
    0.13
    оÑħ
    0.13
    اÙĩ
    0.13
     buck
    0.13
    ØŃر
    0.13
    ÛĮر
    0.12
     '{}'
    0.12
    ByKey
    0.12
    289
    0.12
    Act Density 0.002%

    No Known Activations