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

    Neuronpedia

    INDEX
    Explanations

    familial names and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    18
    -0.26
    13
    -0.26
    19
    -0.25
    11
    -0.25
    12
    -0.24
    14
    -0.24
    15
    -0.23
    16
    -0.21
    17
    -0.20
    20
    -0.20
    POSITIVE LOGITS
     seven
    0.31
    7
    0.29
     six
    0.28
     seventh
    0.26
    6
    0.25
    seven
    0.23
     sixth
    0.23
     ä¸ĥ
    0.23
    ä¸ĥ
    0.22
     five
    0.22
    Act Density 0.070%

    No Known Activations