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

    Neuronpedia

    INDEX
    Explanations

    the presence of the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sp
    -0.59
     has
    -0.59
     from
    -0.57
     check
    -0.57
     and
    -0.56
     as
    -0.56
     first
    -0.56
     entry
    -0.55
     
    -0.55
     was
    -0.55
    POSITIVE LOGITS
     يتيمه
    1.12
     esternos
    1.11
    thâu
    1.10
     незавершена
    1.05
    ThroughAttribute
    1.04
    ]")]
    1.03
    transQ
    1.02
     мәкал
    1.01
     Мексичка
    0.99
    下载附件
    0.99
    Act Density 0.070%

    No Known Activations