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

    Neuronpedia

    INDEX
    Explanations

    numbers that are higher than 7

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, especially related to financial or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ief
    -0.70
     rocks
    -0.70
    iko
    -0.69
     Django
    -0.68
    gemony
    -0.68
     Fram
    -0.67
     Gin
    -0.66
     Xie
    -0.66
    isel
    -0.65
     cheek
    -0.65
    POSITIVE LOGITS
    72
    2.59
    73
    2.02
     72
    1.93
    74
    1.90
    71
    1.87
    1972
    1.41
    572
    1.36
    472
    1.33
    76
    1.33
     71
    1.32
    Act Density 0.042%

    No Known Activations