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

    Neuronpedia

    INDEX
    Explanations

    concepts related to training neural networks and their evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.57
    ulkan
    -0.52
     fechas
    -0.50
     perforation
    -0.50
     Committees
    -0.49
    NewGuid
    -0.49
    tlement
    -0.48
    mercy
    -0.48
     tué
    -0.48
    yaar
    -0.47
    POSITIVE LOGITS
     training
    0.68
     beginnetje
    0.60
    parsedMessage
    0.56
     learn
    0.56
     learning
    0.56
    älde
    0.55
    XmlAccessType
    0.55
    UnusedPrivate
    0.55
     Training
    0.53
    criminator
    0.52
    Act Density 0.754%

    No Known Activations