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

    Neuronpedia

    INDEX
    Explanations

    terms related to destructive actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cosmic or astronomical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [+
    -0.58
     Originally
    -0.56
     lately
    -0.55
     âĢº
    -0.54
     à¨
    -0.52
     pioneered
    -0.49
     anecd
    -0.49
     mentioning
    -0.49
    htaking
    -0.49
     ·
    -0.49
    POSITIVE LOGITS
    )).
    0.83
    livion
    0.81
    ))))
    0.81
    )))
    0.77
     eventual
    0.76
    ]).
    0.73
    %.
    0.73
    ]."
    0.68
     attRot
    0.66
    ãĢĤ
    0.64
    Act Density 2.089%

    No Known Activations