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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or negation

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

    Followed by "only" or variations of "only"

    np_acts-logits-general · gemini-2.0-flash

    the only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.39
    よりは
    -0.36
    更
    -0.35
    abilité
    -0.34
     Cor
    -0.34
    つつ
    -0.34
    fiques
    -0.34
    mes
    -0.34
    肯
    -0.33
    getInputStream
    -0.33
    POSITIVE LOGITS
     един
    1.58
     único
    1.58
     únicos
    1.56
    唯一
    1.54
     única
    1.48
     únicas
    1.48
    唯一的
    1.38
     eneste
    1.37
     seuls
    1.36
     sole
    1.35
    Act Density 0.216%

    No Known Activations