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

    Neuronpedia

    INDEX
    Explanations

    references to various training activities or programs

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

    "training"

    np_acts-logits-general · gemini-2.0-flash

    training and follow-up words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зировать
    -0.59
     TSC
    -0.57
    mbito
    -0.55
     MUNDO
    -0.55
    TSC
    -0.54
    covo
    -0.53
    getStatusCode
    -0.53
    Bson
    -0.53
     Heaven
    -0.52
     teaspoons
    -0.52
    POSITIVE LOGITS
     train
    0.64
     trainings
    0.63
     TRAIN
    0.62
     trains
    0.61
    TRAIN
    0.61
     trein
    0.60
    wreck
    0.60
     Train
    0.59
    0.58
     Affiliations
    0.56
    Act Density 0.148%

    No Known Activations