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

    Neuronpedia

    INDEX
    Explanations

    words appearing in a historical play script

    oai_token-act-pair · gemini-2.0-flash

    textual references related to books or titles

    np_token-act-pair-logits · gpt-4o-mini

    Single characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.55
     raiſ
    -1.39
     Theſe
    -1.35
     myſelf
    -1.34
    ſelves
    -1.31
    ſelf
    -1.30
     ſever
    -1.29
     themſelves
    -1.28
     auffi
    -1.26
     ſtate
    -1.26
    POSITIVE LOGITS
     t
    0.69
     
    0.67
    ,
    0.64
     (
    0.63
     da
    0.61
     G
    0.60
     g
    0.59
     T
    0.57
     as
    0.57
    <eos>
    0.56
    Act Density 3.664%

    No Known Activations