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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formatting tags or control characters in a document

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

    Followed by "The" or a capital letter

    np_acts-logits-general · gemini-2.0-flash

    positive greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.72
    SuppressMessage
    -0.56
    ectoria
    -0.52
     sī
    -0.51
    AndEndTag
    -0.51
    Hochspringen
    -0.49
    Asimismo
    -0.48
    ?<
    -0.47
     beider
    -0.46
     prevede
    -0.46
    POSITIVE LOGITS
    Happy
    0.96
     happy
    0.94
     Happy
    0.94
    happy
    0.91
    HAPPY
    0.83
     HAPPY
    0.82
     Hey
    0.80
    Hey
    0.74
     happier
    0.68
    another
    0.65
    Act Density 0.095%

    No Known Activations