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

    Neuronpedia

    INDEX
    Explanations

    words related to specific locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    the word "vi" in various contexts, indicating a focus on the concept of "visual" or "vision."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.86
    spin
    -0.85
    worthiness
    -0.80
    rooms
    -0.77
    lins
    -0.72
    side
    -0.70
    ees
    -0.69
    master
    -0.68
    lined
    -0.68
    */(
    -0.67
    POSITIVE LOGITS
    Äĩ
    1.34
    orno
    0.98
    ère
    0.98
    utenant
    0.97
    ya
    0.97
    zzle
    0.96
    ña
    0.95
    wi
    0.93
    hei
    0.93
    plom
    0.90
    Act Density 0.090%

    No Known Activations