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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuated statements or sentences in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discreet
    -0.89
     boarded
    -0.85
     abduct
    -0.82
     ambush
    -0.82
     organise
    -0.80
     barric
    -0.79
     agent
    -0.78
     calming
    -0.77
     dere
    -0.76
     befriend
    -0.76
    POSITIVE LOGITS
     Additionally
    1.38
     Conversely
    1.35
     Moreover
    1.34
     Overall
    1.32
     Furthermore
    1.30
     Similarly
    1.29
     Likewise
    1.26
     Meanwhile
    1.25
     Compare
    1.25
     Compared
    1.24
    Act Density 0.417%

    No Known Activations