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

    Neuronpedia

    INDEX
    Explanations

    references to identity verification and related legal or bureaucratic processes

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

    Followed by Japanese particles

    np_acts-logits-general · gemini-2.0-flash

    loan or death after release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.73
    ,
    -0.71
     (
    -0.69
    .
    -0.66
     is
    -0.65
     B
    -0.64
    -
    -0.64
     to
    -0.63
     that
    -0.63
     "
    -0.62
    POSITIVE LOGITS
     itſelf
    1.10
     myſelf
    1.10
     Reſ
    1.08
     ſche
    1.07
     pleaſure
    1.06
     ―――――
    1.06
     Monfieur
    1.05
     auffi
    1.04
     ſever
    1.02
     Theſe
    1.00
    Act Density 0.057%

    No Known Activations