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

    Neuronpedia

    INDEX
    Explanations

    references to specific political figures or public personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zew
    -0.19
    dete
    -0.16
    SES
    -0.16
    вай
    -0.15
    кеÑĤ
    -0.15
    ses
    -0.15
    Readable
    -0.15
    éŀ
    -0.15
    aktu
    -0.14
    CUS
    -0.14
    POSITIVE LOGITS
     indent
    0.16
    Indent
    0.16
    éİ®
    0.15
    indent
    0.15
     Tmax
    0.15
    -indent
    0.14
     Sha
    0.14
    æ½
    0.14
    873
    0.14
    ubbo
    0.14
    Act Density 0.003%

    No Known Activations