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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the size of objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to various dimensions or measurements of size

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.85
    rique
    -0.84
    roit
    -0.83
    perty
    -0.83
    rea
    -0.78
    endez
    -0.76
    INA
    -0.74
    rons
    -0.74
    ICLE
    -0.73
    rov
    -0.72
    POSITIVE LOGITS
     scale
    1.03
     stature
    0.92
     discrepancy
    0.82
     scales
    0.80
     proportions
    0.80
     circumference
    0.79
     size
    0.78
     difference
    0.78
     intestine
    0.78
     mismatch
    0.77
    Act Density 0.041%

    No Known Activations