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

    Neuronpedia

    INDEX
    Explanations

    language related to external factors or conditions influencing a specific subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a connection to various issues or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruary
    -1.03
    AUT
    -0.92
    arest
    -0.88
    matched
    -0.85
    irlf
    -0.82
    enhagen
    -0.80
    ellen
    -0.77
    onest
    -0.76
    elfth
    -0.76
    姫
    -0.75
    POSITIVE LOGITS
     activities
    1.13
     activity
    1.08
     disasters
    1.04
     pursuits
    1.02
     endeavors
    0.99
     phenomena
    0.96
     topics
    0.95
     woes
    0.95
     illnesses
    0.94
     offenses
    0.94
    Act Density 0.063%

    No Known Activations