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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters for a specific letter

    oai_token-act-pair · gpt-3.5-turbo

    patterns in encoded text or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.81
    ifact
    -0.76
    oppable
    -0.76
    ometimes
    -0.73
    emort
    -0.67
    bucks
    -0.66
    ainer
    -0.66
     athlet
    -0.65
    igators
    -0.65
    agonist
    -0.65
    POSITIVE LOGITS
    н
    1.09
    Ñı
    1.01
    д
    1.00
    л
    0.99
    0.98
    ¾
    0.96
    м
    0.95
    Ñ
    0.95
    ÑĤ
    0.94
    ÑĢ
    0.94
    Act Density 0.012%

    No Known Activations