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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and debates

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?".
    -0.77
    ?",
    -0.74
     doesnt
    -0.73
    %"
    -0.73
    )?
    -0.72
    ?ãĢį
    -0.72
    }}}
    -0.71
    cffffcc
    -0.71
    "))
    -0.71
    )).
    -0.71
    POSITIVE LOGITS
     plag
    1.04
     worn
    0.84
     wielded
    0.83
     emanating
    0.83
     belonging
    0.81
     undertaken
    0.81
     among
    0.80
     across
    0.79
     used
    0.79
     aboard
    0.79
    Act Density 0.580%

    No Known Activations