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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "least."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GPU
    -0.86
    CHR
    -0.79
     unavailable
    -0.74
    Bon
    -0.72
     Aval
    -0.71
    WAR
    -0.70
    jection
    -0.69
    Murray
    -0.68
    âĪ
    -0.67
    CHO
    -0.66
    POSITIVE LOGITS
    lest
    1.10
    ength
    1.04
    inus
    0.89
    ritch
    0.86
    avin
    0.85
    ronics
    0.82
    reet
    0.81
     Telescope
    0.81
    rils
    0.78
    anos
    0.77
    Act Density 0.010%

    No Known Activations