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

    Neuronpedia

    INDEX
    Explanations

    instances of specific nouns or proper nouns related to identity or place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkel
    -0.17
    üre
    -0.17
    иÑĨин
    -0.15
    senal
    -0.15
    ritz
    -0.14
    edelta
    -0.14
     Olsen
    -0.14
    coma
    -0.14
    LLU
    -0.14
    atem
    -0.14
    POSITIVE LOGITS
    wor
    0.17
    ãĥ«ãĥķ
    0.15
     Jeremiah
    0.15
    νοÏį
    0.14
    anch
    0.14
     collapsing
    0.14
    ạch
    0.14
     ÑģÑĤол
    0.14
     Lub
    0.14
    ope
    0.14
    Act Density 0.019%

    No Known Activations