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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude or reflect on events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.81
     tremend
    -0.80
     endors
    -0.80
     advoc
    -0.79
     nodd
    -0.78
     advis
    -0.77
     independ
    -0.76
     affili
    -0.76
     commer
    -0.74
     ogre
    -0.74
    POSITIVE LOGITS
     Unable
    1.37
     Eventually
    1.36
     Suddenly
    1.35
     Now
    1.31
     Months
    1.31
     Luckily
    1.26
     Then
    1.26
     Initially
    1.25
     Instead
    1.23
     Growing
    1.23
    Act Density 0.247%

    No Known Activations