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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geh
    -0.16
    taj
    -0.15
    erot
    -0.15
    claimer
    -0.15
    yre
    -0.14
    æĺŃåĴĮ
    -0.14
    ÑĢеж
    -0.13
    ounder
    -0.13
    оÑĢÑĤ
    -0.13
    vider
    -0.13
    POSITIVE LOGITS
    son
    0.45
    sson
    0.36
    sons
    0.33
    SON
    0.29
    ine
    0.24
    ston
    0.21
    angelo
    0.20
    so
    0.20
    सन
    0.20
    sono
    0.19
    Act Density 0.122%

    No Known Activations