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

    Neuronpedia

    INDEX
    Explanations

    financial and statistical terms

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oath
    -0.95
     act
    -0.78
    ĸļ
    -0.77
     endeavour
    -0.71
     decrypt
    -0.68
     condone
    -0.68
     equip
    -0.67
     urge
    -0.66
     freedom
    -0.66
    manship
    -0.66
    POSITIVE LOGITS
    Interest
    1.06
    Newsletter
    1.02
    Advertisement
    1.01
    Compared
    1.00
    Average
    1.00
    Additionally
    0.99
    Still
    0.99
    Compare
    0.98
    Related
    0.98
    Correct
    0.97
    Act Density 0.596%

    No Known Activations