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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with measurements or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wise
    -0.17
    41
    -0.15
    Ìģ
    -0.15
    38
    -0.15
    43
    -0.15
    21
    -0.14
    is
    -0.14
    7
    -0.14
    3
    -0.14
    23
    -0.14
    POSITIVE LOGITS
    00
    0.47
    000
    0.36
    0
    0.34
    Û°Û°
    0.28
    âĤĢ
    0.26
    ï¼IJï¼IJ
    0.24
     zero
    0.23
    -zero
    0.23
    鼶
    0.22
    Ùł
    0.21
    Act Density 0.085%

    No Known Activations