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

    Neuronpedia

    INDEX
    Explanations

    references to the term "ides"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ides."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STER
    -0.68
    iona
    -0.67
    thening
    -0.67
    shaw
    -0.64
     gag
    -0.63
     Kard
    -0.61
    brance
    -0.60
     restraint
    -0.59
    pron
    -0.58
    enegger
    -0.58
    POSITIVE LOGITS
    ides
    1.33
    IDES
    1.22
    ide
    1.17
    IDE
    1.09
    creen
    0.91
    ktop
    0.84
    llah
    0.82
    bum
    0.81
    hare
    0.78
    maid
    0.78
    Act Density 0.009%

    No Known Activations