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

    Neuronpedia

    INDEX
    Explanations

    key emotional descriptors and sentiments associated with personal experiences

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

    Following "the," "as," or numbers

    np_acts-logits-general · gemini-2.0-flash

    "employees represent" | "they need" | "based on"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodedInputStream
    -0.66
     favour
    -0.58
     Suitable
    -0.57
     favor
    -0.57
     Favor
    -0.56
     favoring
    -0.56
     favoured
    -0.56
    Mutagenicity
    -0.55
    Suitable
    -0.54
     گیری
    -0.54
    POSITIVE LOGITS
     przecież
    0.83
     quotidien
    0.64
     ultimately
    0.62
     interag
    0.61
     thousands
    0.60
     millions
    0.60
     milliers
    0.60
     täglich
    0.59
     oftentimes
    0.59
     dagelijks
    0.59
    Act Density 0.504%

    No Known Activations