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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]")]
    -0.55
    Rohy
    -0.52
    ########.
    -0.51
     facilité
    -0.51
     启动
    -0.49
    ColumnHeaders
    -0.48
    bart
    -0.47
     introd
    -0.47
     виправивши
    -0.46
     resear
    -0.45
    POSITIVE LOGITS
    Eventually
    0.89
     Eventually
    0.88
     eventually
    0.87
    eventually
    0.81
     eventual
    0.77
     finally
    0.72
     Finally
    0.72
    Finally
    0.68
     exit
    0.64
    ließlich
    0.64
    Act Density 0.323%

    No Known Activations