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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "yet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yet
    -0.18
    ught
    -0.17
    aes
    -0.16
    ptron
    -0.15
    erte
    -0.15
    ses
    -0.15
    -yellow
    -0.15
    Äįku
    -0.15
    ordo
    -0.15
    aggio
    -0.15
    POSITIVE LOGITS
     somehow
    0.28
    ting
    0.22
    -to
    0.22
     another
    0.20
    tings
    0.20
     again
    0.19
     Another
    0.19
     Somehow
    0.19
    forth
    0.18
    another
    0.18
    Act Density 0.024%

    No Known Activations