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

    Neuronpedia

    INDEX
    Explanations

    sequences and patterns in data structures or tensor manipulations

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

    sequences in recurrent networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.49
    WebVitals
    -0.48
     ainfi
    -0.45
     Partagez
    -0.45
     becauſe
    -0.44
     plegable
    -0.43
     navideño
    -0.43
     againſt
    -0.42
     $_(
    -0.42
    RTLD
    -0.42
    POSITIVE LOGITS
    RNN
    0.47
    
    0.45
    SourceChecksum
    0.39
    Autoritní
    0.39
    rnn
    0.39
    istoitu
    0.39
     longitud
    0.38
    ten
    0.38
    greif
    0.38
     RNN
    0.38
    Act Density 0.141%

    No Known Activations