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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating experience or skill level

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.47
    WithIOException
    -0.46
    })()
    -0.41
    ไง
    -0.40
    ByExample
    -0.40
     esimer
    -0.40
     ligiloj
    -0.40
     allAfrica
    -0.39
    inclusive
    -0.38
    纷纷
    -0.36
    POSITIVE LOGITS
     skilled
    2.05
     experienced
    2.00
    experienced
    1.89
    Experienced
    1.73
     Experienced
    1.72
    skilled
    1.66
     Skilled
    1.63
     trained
    1.61
     knowledgeable
    1.41
     Trained
    1.39
    Act Density 0.108%

    No Known Activations