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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "just" and its variations, indicating recent actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.85
    eventually
    -0.79
    unknownFields
    -0.75
     Eſ
    -0.73
     Efq
    -0.73
     myſelf
    -0.72
    Eventually
    -0.68
    ſelf
    -0.68
     uiteindelijk
    -0.67
     pleaſure
    -0.67
    POSITIVE LOGITS
     finished
    1.01
     completed
    0.81
    finished
    0.81
     recently
    0.77
     finishing
    0.73
     Finished
    0.67
     acabo
    0.65
     acaba
    0.63
     newly
    0.63
    刚刚
    0.63
    Act Density 0.073%

    No Known Activations