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

    Neuronpedia

    INDEX
    Explanations

    references to trained professionals or the concept of training itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    相
    -0.57
    ه
    -0.56
     platform
    -0.50
    рин
    -0.50
    .
    -0.50
    Destination
    -0.49
     péri
    -0.49
    e
    -0.47
    y
    -0.47
     Ed
    -0.47
    POSITIVE LOGITS
     trained
    2.04
     Trained
    1.98
    Trained
    1.95
    trained
    1.89
     taught
    1.67
    taught
    1.52
     Taught
    1.51
     educated
    1.32
     untrained
    1.28
    educated
    1.25
    Act Density 0.129%

    No Known Activations