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

    Neuronpedia

    INDEX
    Explanations

    short forms or abbreviations related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.76
     toile
    -0.74
    redo
    -0.67
     questioning
    -0.60
     vulnerability
    -0.58
     Flavoring
    -0.58
     Notting
    -0.57
    ×Ļ
    -0.57
     chance
    -0.56
     cuff
    -0.55
    POSITIVE LOGITS
    ufact
    0.89
    htar
    0.89
    intosh
    0.86
    ouf
    0.80
    hof
    0.78
    arella
    0.76
    ogi
    0.76
    nih
    0.74
    gage
    0.71
    cular
    0.71
    Act Density 0.606%

    No Known Activations