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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns or personal names in sentences starting with "When"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names associated with specific organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.69
    since
    -0.64
     retaining
    -0.64
    ©¶æ¥µ
    -0.63
    etheless
    -0.62
    angering
    -0.61
    INC
    -0.61
     preserving
    -0.60
     maintaining
    -0.60
    é¾įåĸļ士
    -0.59
    POSITIVE LOGITS
     arrived
    1.13
     arrives
    1.07
     first
    1.06
     debuted
    1.06
     approached
    1.00
     premiered
    0.99
     enters
    0.95
     finally
    0.94
     came
    0.93
     collided
    0.93
    Act Density 0.285%

    No Known Activations