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

    Neuronpedia

    INDEX
    Explanations

    numerical values preceded by a currency symbol

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts or financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.88
     necks
    -0.84
     masc
    -0.82
     neck
    -0.77
     gaze
    -0.77
     governance
    -0.77
     boarded
    -0.77
     personality
    -0.76
     forwarding
    -0.75
     calming
    -0.74
    POSITIVE LOGITS
     Compare
    1.21
     Assuming
    1.20
     Meanwhile
    1.18
     That
    1.17
     Additionally
    1.14
     Alternatively
    1.08
     Compared
    1.04
     Furthermore
    1.03
     Considering
    1.03
     However
    1.02
    Act Density 0.389%

    No Known Activations