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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Stan" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the name "Stan"

    oai_token-act-pair · gpt-4-turbo

    mentions of the name "Stan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sensitive
    -0.76
    shapeshifter
    -0.71
    anwhile
    -0.70
     Gemini
    -0.68
    edged
    -0.66
     classified
    -0.64
     gearing
    -0.64
    女
    -0.63
     statutory
    -0.62
     prevailing
    -0.62
    POSITIVE LOGITS
     Stan
    1.09
    isl
    0.90
    ovan
    0.86
    agar
    0.86
    lins
    0.84
    isle
    0.84
    brook
    0.82
    olt
    0.82
    sonian
    0.79
    onga
    0.79
    Act Density 0.005%

    No Known Activations