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

    Neuronpedia

    INDEX
    Explanations

    strings or sequences that follow specific patterns or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ID
    -0.43
    asal
    -0.43
     déroule
    -0.42
    صف
    -0.41
     rapi
    -0.41
     borrowing
    -0.40
    
    -0.40
     
    -0.40
    我不知道
    -0.40
    <bos>
    -0.39
    POSITIVE LOGITS
     gawas
    0.93
     Вікі
    0.85
     AssemblyTitle
    0.78
     Majefty
    0.75
     unknownFields
    0.74
     myſelf
    0.74
    ellees
    0.73
    uxxxx
    0.73
     Efq
    0.73
     juſt
    0.73
    Act Density 2.656%

    No Known Activations