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

    Neuronpedia

    INDEX
    Explanations

    web article links

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and news content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.74
    pperc
    -0.67
     analogue
    -0.60
    leans
    -0.60
     Ace
    -0.60
     loudspe
    -0.60
     Morse
    -0.59
    yah
    -0.58
     Morris
    -0.58
     Oval
    -0.58
    POSITIVE LOGITS
    tenance
    1.02
    status
    0.81
    ificate
    0.77
    flash
    0.77
    _
    0.75
    zilla
    0.75
    prot
    0.74
    uploads
    0.74
    ãĥŁ
    0.74
    finder
    0.74
    Act Density 0.064%

    No Known Activations