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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a change in social or economic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erenn
    -0.63
     Sau
    -0.61
     Fold
    -0.60
     Ov
    -0.58
    Adds
    -0.58
    ierrez
    -0.58
     Lub
    -0.57
    eger
    -0.57
    Column
    -0.56
    odder
    -0.56
    POSITIVE LOGITS
     consequently
    1.12
     therefore
    1.05
     accordingly
    0.97
     thereof
    0.97
     somehow
    0.94
     thereafter
    0.88
     therein
    0.87
     thereto
    0.86
     moreover
    0.79
     shouldn
    0.78
    Act Density 0.458%

    No Known Activations