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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarification or explanation

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative perspectives or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.79
    atism
    -0.69
    ©¶æ
    -0.65
    achelor
    -0.65
    selage
    -0.62
    ulner
    -0.60
    akery
    -0.58
     outweigh
    -0.57
    Ru
    -0.57
     overcame
    -0.56
    POSITIVE LOGITS
     words
    1.66
    words
    1.36
     contexts
    1.09
    worldly
    1.05
     respects
    1.05
     embodiments
    1.00
     Words
    0.99
     circumstances
    0.98
     cases
    0.98
     instances
    0.95
    Act Density 0.028%

    No Known Activations