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

    Neuronpedia

    INDEX
    Explanations

    organizations, names, and other proper nouns containing specific substrings within longer words

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names related to specific entities or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.84
    PDATE
    -0.76
     convol
    -0.71
     tiss
    -0.70
     Kling
    -0.70
     recl
    -0.69
     lin
    -0.68
    etheless
    -0.67
     LIN
    -0.67
     gobl
    -0.65
    POSITIVE LOGITS
    a
    1.67
    aum
    1.06
    aq
    1.06
    aic
    1.01
    aa
    0.99
    av
    0.97
    aan
    0.95
    ao
    0.94
    A
    0.93
    abad
    0.93
    Act Density 0.085%

    No Known Activations