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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial accounting and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accounting for proportions or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fences
    -0.62
     encountering
    -0.62
     benches
    -0.60
     livest
    -0.59
     sake
    -0.59
     slic
    -0.59
     rooft
    -0.58
    meat
    -0.58
     hypers
    -0.57
     Chili
    -0.56
    POSITIVE LOGITS
    inally
    0.91
    ancy
    0.88
    ates
    0.87
    ately
    0.83
     for
    0.82
    antly
    0.81
    ioned
    0.80
    istically
    0.76
    alion
    0.76
    ants
    0.76
    Act Density 0.021%

    No Known Activations