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

    Neuronpedia

    INDEX
    Explanations

    titles or references to sequels and franchises in film and media

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

    movie sequels and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused68>
    -0.85
    <unused79>
    -0.85
    <unused28>
    -0.85
    [@BOS@]
    -0.85
    <unused41>
    -0.85
    <unused52>
    -0.85
    <unused20>
    -0.85
    <unused43>
    -0.85
    <unused16>
    -0.85
    <unused14>
    -0.85
    POSITIVE LOGITS
     sequel
    0.35
    FI
    0.28
     digo
    0.24
    续
    0.24
     ber
    0.24
    &
    0.23
     later
    0.23
    ;
    0.23
    2
    0.22
    ナル
    0.22
    Act Density 0.010%

    No Known Activations