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

    Neuronpedia

    INDEX
    Explanations

    elements that express artistic creativity and expression

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

    ending in "self"

    np_acts-logits-general · gemini-2.0-flash

    reflexive pronouns and archaic spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.66
    .
    -0.59
    ↵↵↵
    -0.59
     The
    -0.56
    <eos>
    -0.50
    </h5>
    -0.49
     In
    -0.48
     So
    -0.46
     M
    -0.46
    ↵↵
    -0.46
    POSITIVE LOGITS
    ,''
    1.04
    ,’’
    1.00
     myſelf
    0.99
    '',
    0.96
     itſelf
    0.95
    ,”
    0.95
    RectangleBorder
    0.94
    ,’”
    0.91
     Houſe
    0.91
    "',
    0.89
    Act Density 0.410%

    No Known Activations