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

    Neuronpedia

    INDEX
    Explanations

    keywords related to gathering, presenting, and analyzing information or facts

    oai_token-act-pair · gpt-3.5-turbo

    references to factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.75
    ebus
    -0.73
    ModLoader
    -0.73
    Interstitial
    -0.73
    Hop
    -0.71
    ertodd
    -0.68
    taboola
    -0.66
    amiya
    -0.65
    ateurs
    -0.65
    irts
    -0.62
    POSITIVE LOGITS
     surrounding
    1.08
    heet
    1.08
     pertaining
    0.98
     regarding
    0.93
     about
    0.88
    facts
    0.87
    fulness
    0.86
     presented
    0.85
     relating
    0.85
    telling
    0.84
    Act Density 0.030%

    No Known Activations