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

    Neuronpedia

    INDEX
    Explanations

    references to walls or wall-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.17
    -git
    -0.16
    ects
    -0.15
    edis
    -0.15
    BarButtonItem
    -0.15
    etics
    -0.15
    ogue
    -0.15
    dle
    -0.15
    ãĤıãĤĬ
    -0.15
    sus
    -0.14
    POSITIVE LOGITS
    avier
    0.18
    au
    0.17
     ang
    0.17
    ao
    0.17
    aud
    0.16
    ä¼į
    0.16
    -mounted
    0.15
    t
    0.15
    sWith
    0.15
    656
    0.15
    Act Density 0.022%

    No Known Activations