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

    Neuronpedia

    INDEX
    Explanations

    references to university names or academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.66
    assets
    -0.64
    hetically
    -0.63
    itutional
    -0.61
     Senators
    -0.61
    aged
    -0.61
    istar
    -0.60
    idad
    -0.59
    ajor
    -0.59
    ired
    -0.58
    POSITIVE LOGITS
    stal
    1.40
    stals
    1.19
    stall
    1.03
    pter
    0.93
    gian
    0.88
    dom
    0.85
    akov
    0.84
    croft
    0.82
    ng
    0.81
    lene
    0.81
    Act Density 0.055%

    No Known Activations