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

    Neuronpedia

    INDEX
    Explanations

    variants of the suffix "th" in the text, often indicative of ordinal numbers or other specific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emetery
    -0.17
    dol
    -0.15
     RectTransform
    -0.15
    oble
    -0.15
    elly
    -0.14
     NavParams
    -0.14
    elihood
    -0.14
    apg
    -0.14
    athon
    -0.14
    ahat
    -0.14
    POSITIVE LOGITS
     Lever
    0.17
    Idle
    0.14
    illed
    0.14
    olog
    0.14
     pun
    0.14
    arged
    0.14
    orne
    0.13
    IDA
    0.13
    ym
    0.13
     Dup
    0.13
    Act Density 0.034%

    No Known Activations