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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding or summarizing text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal understanding and involvement in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crazy
    -0.80
     poop
    -0.78
     KILL
    -0.77
    ðŁĺ
    -0.73
     Kids
    -0.73
     Chains
    -0.70
     diaper
    -0.70
     Kardash
    -0.69
     fake
    -0.69
     underwear
    -0.68
    POSITIVE LOGITS
     scholarly
    1.28
     methodological
    1.19
     fruitful
    1.09
     eluc
    1.06
     summar
    1.01
     histor
    1.00
     scholars
    0.99
     anthology
    0.98
     scholar
    0.97
     indispensable
    0.95
    Act Density 0.772%

    No Known Activations