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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sequential actions or steps in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.11
     myſelf
    -1.07
     Jefus
    -0.98
     Theſe
    -0.95
    ſelf
    -0.94
     Cæsar
    -0.94
     itſelf
    -0.88
     themſelves
    -0.87
     purpoſe
    -0.85
     Chriſt
    -0.85
    POSITIVE LOGITS
     then
    0.95
     kemudian
    0.87
     eventually
    0.77
     ثم
    0.74
     later
    0.74
    then
    0.70
     rồi
    0.69
     poi
    0.69
    Puis
    0.66
     затем
    0.66
    Act Density 0.291%

    No Known Activations