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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that convey specific meanings or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     churn
    -0.15
    avanaugh
    -0.15
    ahn
    -0.15
    ted
    -0.15
     hang
    -0.15
    aines
    -0.14
    ters
    -0.14
    ve
    -0.14
    link
    -0.14
    room
    -0.14
    POSITIVE LOGITS
    ableObject
    0.18
    OGLE
    0.17
    bands
    0.17
    antry
    0.17
    ValuePair
    0.17
    stants
    0.16
    nard
    0.15
    oenix
    0.15
     íĴ
    0.15
    ology
    0.15
    Act Density 0.008%

    No Known Activations