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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names associated with individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.65
     undermin
    -0.58
     prest
    -0.58
     corrid
    -0.57
     citiz
    -0.56
     advoc
    -0.56
    ãĥ¼ãĥĨ
    -0.55
     predec
    -0.53
     challeng
    -0.52
     Adin
    -0.51
    POSITIVE LOGITS
     ]
    0.72
     ):
    0.71
     )]
    0.71
     )
    0.68
    ;;;;;;;;;;;;
    0.68
     );
    0.68
     Forums
    0.67
     Originally
    0.67
     ].
    0.66
     Says
    0.65
    Act Density 0.578%

    No Known Activations