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

    Neuronpedia

    INDEX
    Explanations

    comparisons of different states or conditions between past and present

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Expand
    -0.54
    Phill
    -0.53
    erous
    -0.51
    uckland
    -0.51
    ococ
    -0.51
    ouse
    -0.51
    ango
    -0.50
    skirts
    -0.49
    rf
    -0.48
    ouses
    -0.48
    POSITIVE LOGITS
     before
    0.89
     twenty
    0.89
     fifteen
    0.89
     thirty
    0.85
     fifty
    0.85
     ages
    0.84
     forty
    0.83
     ten
    0.83
     20
    0.82
     eight
    0.79
    Act Density 0.121%

    No Known Activations