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

    Neuronpedia

    INDEX
    Explanations

    references to the action of deleting elements or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esor
    -0.18
    sted
    -0.15
    egas
    -0.15
    wers
    -0.14
    ÅĻik
    -0.14
    ULSE
    -0.14
    lie
    -0.14
    nic
    -0.14
     tune
    -0.14
    inton
    -0.14
    POSITIVE LOGITS
    odd
    0.17
    ebe
    0.15
    avenport
    0.14
    aat
    0.14
     nets
    0.14
    elden
    0.14
    ÙĪÙĦØ©
    0.14
     quarters
    0.14
    Ī¬
    0.14
    branch
    0.13
    Act Density 0.016%

    No Known Activations