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

    Neuronpedia

    INDEX
    Explanations

    similarities between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to similarities and comparisons between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bern
    -0.74
     bay
    -0.71
    til
    -0.69
    Sky
    -0.66
     boarding
    -0.62
    bers
    -0.61
    mans
    -0.60
    FT
    -0.60
     helicop
    -0.60
     oats
    -0.60
    POSITIVE LOGITS
     similarities
    0.99
    lihood
    0.98
     between
    0.87
     resemblance
    0.86
    DragonMagazine
    0.84
    alities
    0.84
     twins
    0.84
     Between
    0.80
    alogy
    0.79
    xual
    0.78
    Act Density 0.033%

    No Known Activations