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

    Neuronpedia

    INDEX
    Explanations

    coding syntax such as special characters and commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts related to significant numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.84
    abouts
    -0.64
    rad
    -0.62
    boro
    -0.61
     footing
    -0.58
    athe
    -0.57
     Torch
    -0.56
     affection
    -0.55
    ijing
    -0.55
    ython
    -0.55
    POSITIVE LOGITS
    Likewise
    0.90
    Furthermore
    0.84
    Moreover
    0.83
    Similarly
    0.82
    Nevertheless
    0.82
    Nonetheless
    0.82
    ³³³³
    0.82
    Therefore
    0.80
    However
    0.80
    Newsletter
    0.76
    Act Density 0.576%

    No Known Activations