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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematics and algebraic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbon
    -0.17
    ldr
    -0.16
     Carbon
    -0.15
     Gür
    -0.15
    åĽ
    -0.14
    entrant
    -0.14
     freedoms
    -0.13
     meter
    -0.13
    _ie
    -0.13
     bill
    -0.13
    POSITIVE LOGITS
     rings
    0.34
     Rings
    0.32
     ring
    0.31
     Ring
    0.28
    Ring
    0.27
    ring
    0.25
    -ring
    0.25
     modules
    0.23
    _ring
    0.23
    RING
    0.23
    Act Density 0.024%

    No Known Activations