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

    Neuronpedia

    INDEX
    Explanations

    references to temporal sequences and patterns in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovah
    -0.19
    eah
    -0.16
    iae
    -0.16
     Jar
    -0.14
    foon
    -0.14
     fit
    -0.13
    fait
    -0.13
     Rh
    -0.13
    Rh
    -0.13
    tuÄŁ
    -0.13
    POSITIVE LOGITS
     day
    0.21
     денÑĮ
    0.17
     month
    0.17
     inning
    0.16
    Projection
    0.15
    æĹ¥ãģ«
    0.15
     week
    0.15
    igits
    0.15
    mvc
    0.14
    .ds
    0.14
    Act Density 0.211%

    No Known Activations