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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing large or extensive things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.74
    --+
    -0.70
    cial
    -0.70
    utral
    -0.70
    ople
    -0.69
    cy
    -0.66
    ordan
    -0.66
    yl
    -0.65
    ivan
    -0.65
    saf
    -0.63
    POSITIVE LOGITS
     sprawling
    1.08
     horizont
    0.84
     expans
    0.74
     conglomer
    0.72
     campus
    0.71
     mammoth
    0.70
     neoc
    0.69
    halla
    0.68
     unbeliev
    0.68
     schizophren
    0.68
    Act Density 0.017%

    No Known Activations