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

    Neuronpedia

    INDEX
    Explanations

    comparative descriptions expressing a degree of difference

    oai_token-act-pair · gpt-3.5-turbo

    comparative adjectives and adverbs related to levels and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enery
    -0.66
    ools
    -0.64
     Penal
    -0.64
    roots
    -0.61
    tein
    -0.61
    ille
    -0.60
     governors
    -0.60
    iliary
    -0.60
    unts
    -0.59
    elf
    -0.59
    POSITIVE LOGITS
     enough
    0.82
     paced
    0.79
     proport
    0.77
    intendent
    0.76
     compared
    0.75
     fluctuations
    0.69
    luster
    0.69
     (<
    0.69
     underest
    0.69
     fluct
    0.66
    Act Density 0.185%

    No Known Activations