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

    Neuronpedia

    INDEX
    Explanations

    numerical values from a financial context

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly in financial or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateurs
    -0.55
    amera
    -0.55
    anchester
    -0.54
    successfully
    -0.54
    okin
    -0.54
     remem
    -0.54
    shots
    -0.54
     Gardens
    -0.53
    natureconservancy
    -0.53
     explan
    -0.53
    POSITIVE LOGITS
    /+
    1.57
    /-
    1.29
     sqor
    0.98
    dB
    0.94
    -+-+-+-+
    0.88
    ï¸ı
    0.83
    -+-+
    0.83
    --+
    0.80
     dB
    0.73
    =-=-=-=-=-=-=-=-
    0.72
    Act Density 0.115%

    No Known Activations