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

    Neuronpedia

    INDEX
    Explanations

    words related to colors and flavors

    oai_token-act-pair · gpt-3.5-turbo

    references to color and flavor in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alter
    -0.87
    eda
    -0.85
    lde
    -0.81
    lust
    -0.80
    asin
    -0.78
    nea
    -0.78
    hner
    -0.77
    ada
    -0.77
    ports
    -0.76
    ommel
    -0.76
    POSITIVE LOGITS
     versions
    0.83
    nesday
    0.78
     seating
    0.77
     coff
    0.75
     goods
    0.73
    rive
    0.72
     ones
    0.72
     subur
    0.71
    irect
    0.71
     copies
    0.70
    Act Density 0.134%

    No Known Activations