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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or symbols, particularly related to statistical or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.71
    ingham
    -0.70
    arily
    -0.63
    inary
    -0.63
     coales
    -0.59
     Kag
    -0.58
     renal
    -0.58
     ESV
    -0.58
     Hindu
    -0.58
    owicz
    -0.57
    POSITIVE LOGITS
    ?)
    0.94
    >)
    0.90
    ?),
    0.89
    !)
    0.87
    ?).
    0.83
     ?)
    0.80
    /-
    0.76
    _-
    0.75
    ...)
    0.74
    fw
    0.72
    Act Density 0.012%

    No Known Activations