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

    Neuronpedia

    INDEX
    Explanations

    references to specific educational institutions, particularly the University of California and the University of Texas at Austin

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions, particularly universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.74
     clutch
    -0.65
     trough
    -0.62
    flame
    -0.62
     courtesy
    -0.59
    elist
    -0.59
    draw
    -0.59
     blu
    -0.59
    orget
    -0.58
     episodes
    -0.58
    POSITIVE LOGITS
    ña
    0.84
    sylvania
    0.67
    igham
    0.66
    IVERS
    0.65
    braska
    0.64
    arijuana
    0.63
    ACA
    0.63
    abulary
    0.62
    ħ
    0.62
    ãĤ¼ãĤ¦ãĤ¹
    0.62
    Act Density 0.105%

    No Known Activations