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

    Neuronpedia

    INDEX
    Explanations

    Russian Cyrillic characters and phrases, specifically focusing on the character "±"

    oai_token-act-pair · gpt-3.5-turbo

    a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     board
    -0.74
     load
    -0.65
     biography
    -0.65
     marker
    -0.64
     copy
    -0.63
     page
    -0.62
     mate
    -0.61
     seat
    -0.61
     messenger
    -0.60
     Mos
    -0.60
    POSITIVE LOGITS
    ±
    4.48
    ·
    2.01
    ³
    1.91
    ²
    1.84
    ´
    1.76
    °
    1.74
    ¹
    1.72
    ¿
    1.72
    ¾
    1.71
    1.69
    Act Density 0.006%

    No Known Activations