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

    Neuronpedia

    INDEX
    Explanations

    numerical representations of sizes or dimensions in square footage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADDE
    -0.16
    rome
    -0.15
    á»ĭch
    -0.15
    thal
    -0.14
    isse
    -0.14
    ighton
    -0.14
    casts
    -0.13
    ima
    -0.13
    æĤł
    -0.13
    wald
    -0.13
    POSITIVE LOGITS
     square
    0.47
     sq
    0.45
    -square
    0.41
    sq
    0.40
     sf
    0.39
    square
    0.38
     Sq
    0.38
    sf
    0.38
     SF
    0.35
    Sq
    0.34
    Act Density 0.023%

    No Known Activations