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

    Neuronpedia

    INDEX
    Explanations

    words related to personal achievements and professional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.51
     deras
    -0.48
     γε
    -0.44
     kema
    -0.43
     Erfindung
    -0.41
     toiminta
    -0.41
     şeyler
    -0.40
     vaikka
    -0.40
    !
    -0.40
    primaryStage
    -0.39
    POSITIVE LOGITS
    "},
    0.89
    ]--;
    0.87
    StructEnd
    0.87
    ]),
    0.85
    "),
    0.85
    ")));
    0.84
    '),
    0.84
    )");
    0.82
    "):
    0.82
    "],
    0.81
    Act Density 0.232%

    No Known Activations