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

    Neuronpedia

    INDEX
    Explanations

    situations where work is mentioned or implied

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words that indicate relationships between ideas or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imum
    -0.74
     Worm
    -0.72
    utt
    -0.70
    worms
    -0.69
     worms
    -0.68
     Redux
    -0.64
    arily
    -0.63
     tsun
    -0.62
    alis
    -0.61
     tsunami
    -0.61
    POSITIVE LOGITS
     pensions
    1.13
     leisure
    1.01
    student
    0.98
    actionDate
    0.94
     academia
    0.91
     residences
    0.90
     exams
    0.89
     hobbies
    0.89
    Student
    0.87
     student
    0.85
    Act Density 0.177%

    No Known Activations