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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoying, experiencing, or interacting with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ending or concluding events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.57
    los
    -0.56
     disbanded
    -0.52
     Reconstruction
    -0.52
    Ń
    -0.51
    Bridge
    -0.51
    ¬¼
    -0.51
     Internal
    -0.51
     instituted
    -0.50
     Historically
    -0.49
    POSITIVE LOGITS
     yourself
    1.33
     yourselves
    1.23
     Yourself
    0.94
     your
    0.87
     YOUR
    0.79
    your
    0.69
    Your
    0.63
     Your
    0.60
     browsing
    0.59
    omet
    0.58
    Act Density 0.732%

    No Known Activations