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

    Neuronpedia

    INDEX
    Explanations

    references to specific subjects and entities in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skar
    -0.40
    nshaw
    -0.38
     Swag
    -0.38
    anat
    -0.36
     Acrobat
    -0.36
     XZ
    -0.36
    terase
    -0.36
     dead
    -0.35
     SRI
    -0.35
    setVerticalGroup
    -0.35
    POSITIVE LOGITS
    -------------</
    0.66
     الحره
    0.54
     Италијани
    0.54
    GenerationType
    0.50
    发表于
    0.50
    PreferredItem
    0.49
     صوتيه
    0.48
     AssemblyCulture
    0.48
    UrlResolution
    0.47
    istoitu
    0.47
    Act Density 0.078%

    No Known Activations