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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "come" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edBy
    -0.14
    ample
    -0.14
     Morse
    -0.14
    ÑĤÑĮÑģÑı
    -0.14
    ovolta
    -0.14
    urtle
    -0.14
    orses
    -0.14
     yok
    -0.13
    ashtra
    -0.13
    ased
    -0.13
    POSITIVE LOGITS
    backs
    0.21
     away
    0.21
     correct
    0.19
     oh
    0.18
     tantal
    0.17
     correcting
    0.17
     nowhere
    0.16
     Away
    0.16
    olini
    0.16
    zel
    0.16
    Act Density 0.028%

    No Known Activations