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

    Neuronpedia

    INDEX
    Explanations

    words related to professions or academic subjects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ry"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.72
    assets
    -0.65
    aged
    -0.64
    hetically
    -0.62
    itutional
    -0.62
    istar
    -0.61
    enaries
    -0.60
    aminer
    -0.59
    istance
    -0.59
    ired
    -0.59
    POSITIVE LOGITS
    stal
    1.41
    stals
    1.28
    pter
    1.02
    stall
    0.97
    akov
    0.89
    gian
    0.88
    lene
    0.85
    kus
    0.83
    âķIJâķIJ
    0.82
    croft
    0.82
    Act Density 0.031%

    No Known Activations