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

    Neuronpedia

    INDEX
    Explanations

    official websites and related announcements or information

    oai_token-act-pair · gpt-3.5-turbo

    references to official sites or official announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.69
    conservancy
    -0.62
    facebook
    -0.59
    ãĥ©ãĥ³
    -0.58
    ãĤ¦ãĤ¹
    -0.57
    ãĥķãĤ©
    -0.57
    phony
    -0.56
    ãĥĥãĥī
    -0.55
    azz
    -0.55
     taps
    -0.54
    POSITIVE LOGITS
     Entered
    0.66
    oca
    0.60
    opted
    0.58
     Destination
    0.57
     Pt
    0.56
    Stage
    0.56
     absorbs
    0.56
     Learns
    0.56
    Ĥİ
    0.54
     tong
    0.53
    Act Density 0.994%

    No Known Activations