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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human interaction and personal reflection

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to emotional support and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reportedly
    -0.58
     largeDownload
    -0.58
     Arri
    -0.57
     Reported
    -0.56
     ARM
    -0.54
     FG
    -0.53
     shipments
    -0.52
     Cosponsors
    -0.52
     PHOTO
    -0.52
     Latest
    -0.51
    POSITIVE LOGITS
     someday
    0.63
     anymore
    0.62
     meaningful
    0.58
     selves
    0.54
     darn
    0.53
     wiser
    0.53
    )),
    0.51
    poke
    0.51
    )).
    0.51
    udic
    0.51
    Act Density 4.329%

    No Known Activations