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

    Neuronpedia

    INDEX
    Explanations

    phrases related to incidents, conflicts, or massive actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal issues and cultural critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.67
    vertising
    -0.63
    yna
    -0.61
    bledon
    -0.61
    rive
    -0.60
     mathemat
    -0.59
    dinand
    -0.56
    âĢij
    -0.55
     neighb
    -0.55
    Īè
    -0.55
    POSITIVE LOGITS
     ]
    1.42
     ):
    1.42
     )
    1.35
     ].
    1.25
     Âł
    1.25
     ))
    1.23
     ),
    1.23
    ↵Âł
    1.21
     );
    1.21
     ,"
    1.19
    Act Density 0.600%

    No Known Activations