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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measurements or rates expressed as "per" followed by a unit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.40
    ImageData
    -0.39
     ruine
    -0.38
    ophage
    -0.37
     voile
    -0.35
    <mask>
    -0.35
    writeHead
    -0.35
    IImage
    -0.35
    ArgumentParser
    -0.34
    enskap
    -0.34
    POSITIVE LOGITS
     per
    1.45
     Per
    1.15
    Per
    1.11
     PER
    1.01
    per
    0.98
     every
    0.96
     each
    0.91
     bawat
    0.83
     tiap
    0.82
    every
    0.81
    Act Density 0.163%

    No Known Activations