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

    Neuronpedia

    INDEX
    Explanations

    Ampersands connecting two entities

    oai_token-act-pair · gpt-3.5-turbo

    ampersands used for collaborations or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -1.09
     misunder
    -0.93
    atche
    -0.86
    Downloadha
    -0.85
    nces
    -0.81
    govtrack
    -0.80
    paralle
    -0.76
    senal
    -0.73
    iversal
    -0.73
    ionage
    -0.72
    POSITIVE LOGITS
     Friends
    0.85
     Sons
    0.81
    GAN
    0.79
     Associates
    0.75
    ++++++++++++++++
    0.74
    #$
    0.73
    optional
    0.73
     Company
    0.71
     Co
    0.70
     vice
    0.67
    Act Density 0.019%

    No Known Activations