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

    Neuronpedia

    INDEX
    Explanations

    numbers and special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "²"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transmitter
    -0.69
     cle
    -0.69
     order
    -0.68
     assignment
    -0.64
     Cop
    -0.63
     compet
    -0.62
     DH
    -0.62
     sample
    -0.61
     brace
    -0.60
     cad
    -0.60
    POSITIVE LOGITS
    ²
    4.36
    ³
    2.00
    ¼
    1.99
    ¾
    1.97
    ¹
    1.95
    ¿
    1.93
    ¬
    1.91
    ±
    1.90
    1.86
    ¸
    1.85
    Act Density 0.004%

    No Known Activations