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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its effects on sentence structure

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

    Text after commas

    np_acts-logits-general · gemini-2.0-flash

    list or clause separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.79
    EDEFAULT
    -0.78
    EndProject
    -0.74
    ագրություններ
    -0.71
     oprot
    -0.70
     doubtnut
    -0.70
    Ссылки
    -0.67
     esternos
    -0.67
     pleaſure
    -0.66
     Jefus
    -0.66
    POSITIVE LOGITS
     or
    0.71
     and
    0.52
     fe
    0.48
    以及
    0.47
     fé
    0.47
    或者是
    0.46
     یا
    0.45
    ”、“
    0.45
    Clik
    0.45
    or
    0.44
    Act Density 0.612%

    No Known Activations