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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and symbols organized in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayson
    -0.63
     Nare
    -0.61
    agra
    -0.59
     Vaugh
    -0.57
     Seym
    -0.57
    emale
    -0.55
    oppable
    -0.55
    acebook
    -0.54
     Jagu
    -0.54
    engeance
    -0.53
    POSITIVE LOGITS
     largeDownload
    0.74
     unders
    0.59
     Psy
    0.59
    zbollah
    0.58
     embodiments
    0.56
    mosp
    0.52
    externalActionCode
    0.52
     subp
    0.51
    annabin
    0.50
     TRUMP
    0.50
    Act Density 0.980%

    No Known Activations