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

    Neuronpedia

    INDEX
    Explanations

    terminology related to training and learning processes

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

    the word "training" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     dieux
    -0.41
     miniaturka
    -0.36
     pingente
    -0.36
     alfombra
    -0.33
     cuenca
    -0.33
     Vgl
    -0.33
     kalite
    -0.32
     burbujas
    -0.32
     Italij
    -0.32
     Zelanda
    -0.32
    POSITIVE LOGITS
    wreck
    0.58
    Havolalar
    0.54
    addGap
    0.54
     MainAxisSize
    0.52
    Train
    0.52
    WriteLiteral
    0.51
    -------------</
    0.51
     GTO
    0.50
    Искәрмәләр
    0.50
     Train
    0.50
    Act Density 0.141%

    No Known Activations