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

    Neuronpedia

    INDEX
    Explanations

    words or phrases associated with numerical data, especially in a context related to statistics or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    777
    -0.16
    oga
    -0.15
    181
    -0.15
    leen
    -0.14
     amb
    -0.14
    le
    -0.14
    180
    -0.14
    acha
    -0.14
    ther
    -0.13
    165
    -0.13
    POSITIVE LOGITS
    å¹´
    0.25
    ëħĦëıĦ
    0.21
    欧
    0.21
     ëħĦ
    0.21
     marks
    0.20
    ëħĦ
    0.20
    -present
    0.20
     yılı
    0.19
     å¹´
    0.19
    marks
    0.18
    Act Density 0.094%

    No Known Activations