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

    Neuronpedia

    INDEX
    Explanations

    questions or queries

    oai_token-act-pair · gpt-3.5-turbo

    iterations of the word "what" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tide
    -0.66
     fixme
    -0.62
    piece
    -0.61
    Ļ½
    -0.60
     Blazers
    -0.56
    Tex
    -0.56
     Packers
    -0.56
    jee
    -0.56
     Oy
    -0.55
    xon
    -0.55
    POSITIVE LOGITS
     constitutes
    0.95
     transpired
    0.94
     happened
    0.92
     constituted
    0.91
     happens
    0.88
    soever
    0.88
    ãĤ¼ãĤ¦ãĤ¹
    0.87
    Downloadha
    0.80
    onga
    0.77
     happ
    0.75
    Act Density 0.045%

    No Known Activations