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

    Neuronpedia

    INDEX
    Explanations

    pairs of contrasting terms

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uel
    -0.79
    ³
    -0.75
    odore
    -0.71
    į
    -0.71
    iane
    -0.70
    Ĥª
    -0.69
    IJ
    -0.68
    Į
    -0.68
    º
    -0.68
    eks
    -0.66
    POSITIVE LOGITS
     ours
    0.72
     halves
    0.72
     sexes
    0.70
     autobiography
    0.66
    ebook
    0.62
    nam
    0.62
     equally
    0.60
     multiplication
    0.60
     genders
    0.59
     admit
    0.59
    Act Density 0.148%

    No Known Activations