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

    Neuronpedia

    INDEX
    Explanations

    various forms of communication and negotiation discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Month
    -0.35
     month
    -0.34
     Months
    -0.32
     Weeks
    -0.32
    Month
    -0.31
    Months
    -0.31
    months
    -0.29
     monthly
    -0.29
    month
    -0.28
     months
    -0.28
    POSITIVE LOGITS
     morning
    0.54
     hours
    0.53
     afternoon
    0.50
     evening
    0.49
     late
    0.45
     hour
    0.44
     Hours
    0.44
    hours
    0.43
     overnight
    0.43
    æĻļ
    0.42
    Act Density 0.224%

    No Known Activations