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

    Neuronpedia

    INDEX
    Explanations

    programming-related structures or syntax elements

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

    Tokens followed by "len"

    np_acts-logits-general · gemini-2.0-flash

    Papa Kenn Len

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Butterfield
    -0.67
     McRae
    -0.64
     Warburton
    -0.62
     Guille
    -0.57
     Fulda
    -0.56
     Stubbs
    -0.55
    ITIC
    -0.54
     Falk
    -0.53
     Elias
    -0.53
     Schwal
    -0.53
    POSITIVE LOGITS
     Len
    1.30
     Ken
    1.25
     len
    1.23
    Ken
    1.22
     CEN
    1.19
    Len
    1.19
     LEN
    1.18
     Wen
    1.16
    len
    1.14
     DEN
    1.11
    Act Density 0.554%

    No Known Activations