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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "address" in various forms, such as its base form and different conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viz
    -0.17
    ediator
    -0.17
    еÑĢеÑĩ
    -0.15
    IGHL
    -0.15
    Ñħа
    -0.15
    isi
    -0.15
    iero
    -0.15
    ané
    -0.15
    irim
    -0.14
    kup
    -0.14
    POSITIVE LOGITS
    (es
    0.24
    able
    0.22
    ABLE
    0.18
    esine
    0.18
     addr
    0.18
    ses
    0.17
    ional
    0.17
    orial
    0.17
    ion
    0.15
    ë¡Ŀ
    0.15
    Act Density 0.036%

    No Known Activations