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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ethics or social issues

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Entered
    -0.70
     Employees
    -0.58
    iny
    -0.57
    andals
    -0.56
    USS
    -0.55
    icial
    -0.55
    OME
    -0.54
    utive
    -0.54
    erv
    -0.54
    olo
    -0.52
    POSITIVE LOGITS
     regardless
    1.30
     albeit
    1.29
     irrespective
    1.27
     although
    1.12
     preferably
    1.08
     but
    1.07
     insofar
    1.06
     whereas
    1.04
     though
    1.02
     huh
    1.00
    Act Density 0.412%

    No Known Activations