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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to geometric shapes, particularly hexagons and pentagons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quals
    -0.15
     Croat
    -0.15
     Dillon
    -0.14
    quee
    -0.14
    еÑĢк
    -0.14
    _NR
    -0.14
    ieber
    -0.14
    isations
    -0.14
    sink
    -0.14
     Cro
    -0.14
    POSITIVE LOGITS
    agonal
    0.30
    agon
    0.24
     Pent
    0.21
    AGON
    0.20
    adecimal
    0.19
    /oct
    0.19
    athlon
    0.19
    pent
    0.18
    tet
    0.17
    agram
    0.17
    Act Density 0.021%

    No Known Activations