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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically apostrophes and quotation marks

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

    quoted contractions and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vecino
    -0.40
     <<<<<<<<<<<<<<
    -0.40
    GOTREF
    -0.38
     consultato
    -0.33
    GTCX
    -0.32
     contemporaine
    -0.32
     contemporáneo
    -0.31
     vermelhas
    -0.30
     orgánico
    -0.30
    addPreferredGap
    -0.29
    POSITIVE LOGITS
     queſta
    0.77
     incrí
    0.72
    ']]
    0.71
    0.71
    ’”
    0.71
     $_"
    0.69
    𓂸
    0.69
    <unused0>
    0.69
    ❳
    0.68
    EnglishChoose
    0.68
    Act Density 0.031%

    No Known Activations