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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with locations and urban contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asive
    -0.15
    ussy
    -0.15
    grade
    -0.15
    ayne
    -0.15
    acement
    -0.15
    FRING
    -0.14
    ansom
    -0.14
    upo
    -0.14
    utilus
    -0.14
    emand
    -0.14
    POSITIVE LOGITS
    tl
    0.18
    ase
    0.17
    onium
    0.16
    ither
    0.14
    ities
    0.14
    weg
    0.14
    ö
    0.14
    .terminate
    0.14
    à¸ģ
    0.14
    anka
    0.14
    Act Density 0.096%

    No Known Activations