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

    Neuronpedia

    INDEX
    Explanations

    phrases related to learning and improvement

    oai_token-act-pair · gpt-3.5-turbo

    key concepts and terms related to lessons and analysis of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bulldogs
    -0.64
     Richards
    -0.62
    iasis
    -0.60
     Daytona
    -0.57
    ILE
    -0.57
    Brother
    -0.57
    MENT
    -0.56
    ת
    -0.56
     Peel
    -0.56
     Staten
    -0.55
    POSITIVE LOGITS
    peed
    1.28
    mith
    1.26
    poon
    1.18
    afety
    1.14
    pread
    1.09
    pace
    1.09
    hare
    1.08
    pring
    1.06
    hift
    1.04
    cape
    1.04
    Act Density 0.507%

    No Known Activations