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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of large numerical values, particularly those presented with commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advoc
    -0.61
     newsp
    -0.61
     reperto
    -0.61
     resemb
    -0.61
     streng
    -0.60
     likeness
    -0.60
     Anarchy
    -0.60
     fundamentals
    -0.60
     behav
    -0.59
    eers
    -0.58
    POSITIVE LOGITS
    000
    2.27
     000
    1.42
    00
    1.34
    0000
    1.34
    600
    1.19
    500
    1.19
    700
    1.16
    0002
    1.16
    800
    1.13
    400
    1.13
    Act Density 0.048%

    No Known Activations