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

    Neuronpedia

    INDEX
    Explanations

    locations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.75
    ppings
    -0.69
    ]).
    -0.68
     misses
    -0.62
     carnage
    -0.60
    VERTISEMENT
    -0.59
    uddenly
    -0.59
    OULD
    -0.59
     sooner
    -0.58
     insult
    -0.57
    POSITIVE LOGITS
     whereas
    1.07
     although
    0.98
     whose
    0.94
     consisting
    0.92
     flanked
    0.91
     which
    0.88
     but
    0.84
    ;
    0.84
     comprising
    0.76
     alongside
    0.73
    Act Density 0.661%

    No Known Activations