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

    Neuronpedia

    INDEX
    Explanations

    words related to the term "raisins."

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of a specific sequence of letters or syllables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MacArthur
    -0.75
    ij士
    -0.73
     Izan
    -0.66
     Translation
    -0.66
     Geo
    -0.66
     Dispatch
    -0.65
     Intelligent
    -0.65
     Chau
    -0.65
     Asians
    -0.64
     Spur
    -0.64
    POSITIVE LOGITS
    fters
    1.26
    ven
    1.05
     ra
    0.99
    wn
    0.98
    isin
    0.92
    uth
    0.90
    fter
    0.90
    vel
    0.88
    uble
    0.88
    pt
    0.88
    Act Density 0.006%

    No Known Activations