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

    Neuronpedia

    INDEX
    Explanations

    references to the word "til" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yor
    -0.17
    acht
    -0.17
    enza
    -0.16
    ência
    -0.14
    ÑģÑĤи
    -0.14
    sdale
    -0.14
    obi
    -0.14
    esso
    -0.14
    аниÑĨ
    -0.14
    vais
    -0.14
    POSITIVE LOGITS
    apia
    0.27
    ting
    0.21
    ahun
    0.20
     death
    0.19
    -death
    0.18
    isateur
    0.17
    icho
    0.17
    gers
    0.17
    brook
    0.16
     tit
    0.16
    Act Density 0.027%

    No Known Activations