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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ies" in texts

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific suffix in words, particularly "ies."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acia
    -0.79
    ivities
    -0.78
    adium
    -0.78
    wcsstore
    -0.77
    ivity
    -0.72
    atever
    -0.72
    IENT
    -0.72
    ances
    -0.71
    icter
    -0.71
    iffs
    -0.70
    POSITIVE LOGITS
    ystem
    0.85
    eries
    0.84
    ea
    0.79
    cence
    0.74
    hl
    0.73
    e
    0.72
    utenant
    0.71
    pace
    0.70
    anders
    0.69
    ery
    0.67
    Act Density 0.034%

    No Known Activations