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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or actions in sports and current affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ));
    -0.64
     fortunate
    -0.60
     behavi
    -0.59
    reporting
    -0.57
    ibaba
    -0.55
    milo
    -0.53
     blight
    -0.52
    onga
    -0.51
     upt
    -0.49
     fortun
    -0.49
    POSITIVE LOGITS
    ]
    3.04
    ?]
    2.81
    !]
    2.80
    .]
    2.72
    ']
    2.72
    ]"
    2.72
    :]
    2.65
    ...]
    2.64
    ]:
    2.61
    ].
    2.59
    Act Density 0.205%

    No Known Activations