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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    houses
    -0.17
    house
    -0.16
    ãĥ£
    -0.16
    Ïį
    -0.16
    تÙĪÙĨ
    -0.16
    hoe
    -0.16
    t
    -0.15
    tober
    -0.15
    tas
    -0.15
    tan
    -0.15
    POSITIVE LOGITS
    cular
    0.24
    UARIO
    0.21
    ser
    0.20
    yne
    0.19
    cript
    0.19
     Maxim
    0.18
    aurus
    0.18
    663
    0.18
    son
    0.18
    zc
    0.17
    Act Density 0.078%

    No Known Activations