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

    Neuronpedia

    INDEX
    Explanations

    instances of the root "Rec" followed by different suffixes or contexts related to recommendations or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with Rec

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.64
     Plural
    -0.60
    AnimationsModule
    -0.59
     Roskov
    -0.59
    ConverterFactory
    -0.58
     Svensson
    -0.57
    /**
    -0.57
    RegressionTest
    -0.56
     nahilalakip
    -0.56
    <bos>
    -0.56
    POSITIVE LOGITS
     Rec
    0.99
    Rec
    0.98
     REC
    0.49
    ſelf
    0.48
    Rel
    0.47
     atque
    0.45
    Ret
    0.44
     Ret
    0.44
     Re
    0.43
     jį
    0.42
    Act Density 0.012%

    No Known Activations