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

    Neuronpedia

    INDEX
    Explanations

    instances of specific numerical or coding patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uet
    -0.17
    ulis
    -0.15
    isure
    -0.14
    keys
    -0.14
    ucc
    -0.14
    .volley
    -0.14
    uang
    -0.14
    olean
    -0.14
    ç»ĩ
    -0.13
    rael
    -0.13
    POSITIVE LOGITS
    rd
    0.25
    -quarters
    0.19
    antasy
    0.18
    ï¸ı
    0.16
     independent
    0.16
    ehler
    0.15
    iddy
    0.15
    920
    0.15
     Independent
    0.14
    fold
    0.14
    Act Density 0.160%

    No Known Activations