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

    Neuronpedia

    INDEX
    Explanations

    amounts of money or statistical figures

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abduct
    -0.84
     imperson
    -0.79
     pse
    -0.79
     volunte
    -0.78
     carbohyd
    -0.76
     electr
    -0.75
     necks
    -0.75
     affili
    -0.74
     boarded
    -0.74
     guise
    -0.72
    POSITIVE LOGITS
     That
    1.60
     Assuming
    1.57
     Compare
    1.57
     Considering
    1.44
     Meanwhile
    1.36
     Compared
    1.34
     Including
    1.26
     Therefore
    1.23
     Granted
    1.23
     Additionally
    1.22
    Act Density 0.316%

    No Known Activations