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

    Neuronpedia

    INDEX
    Explanations

    references to things being similar or alike

    oai_token-act-pair · gpt-3.5-turbo

    references to similar actions or statements across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accordingly
    -0.63
    maximum
    -0.58
    otta
    -0.58
     whatever
    -0.57
     whichever
    -0.57
    bart
    -0.56
     PLEASE
    -0.56
    #$
    -0.55
    CHAPTER
    -0.54
     preferably
    -0.52
    POSITIVE LOGITS
     elsewhere
    1.12
     earlier
    1.11
     similar
    0.98
     similarly
    0.97
     previous
    0.92
     unsuccessfully
    0.91
     previously
    0.82
     unsuccessful
    0.77
     Earlier
    0.73
     other
    0.73
    Act Density 0.515%

    No Known Activations