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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and possessive forms

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

    Character following an apostrophe or number

    np_acts-logits-general · gemini-2.0-flash

    numbers and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     –,
    -0.79
     ─
    -0.76
     [{
    -0.69
     ▼
    -0.68
     '\\;'
    -0.67
    ’”
    -0.65
    、“
    -0.63
    ]),
    -0.63
    .–
    -0.63
     ――
    -0.63
    POSITIVE LOGITS
     I
    0.87
     ppl
    0.67
     :)
    0.65
     it
    0.64
     nice
    0.64
     دیگه
    0.63
     guys
    0.63
    şey
    0.63
     my
    0.62
     stupid
    0.62
    Act Density 0.179%

    No Known Activations