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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets related to specific functions or features

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    owship
    -1.22
    hound
    -1.04
    hood
    -1.03
    pub
    -1.02
    nesty
    -1.01
    si
    -1.00
    volent
    -0.99
    uberty
    -0.98
    heit
    -0.98
    nd
    -0.94
    POSITIVE LOGITS
     sparing
    1.01
     inputs
    0.98
     contacts
    0.97
     partName
    0.96
     materials
    0.96
     needles
    0.96
    BUS
    0.94
     scraps
    0.93
     computers
    0.93
    ITE
    0.92
    Act Density 0.448%

    No Known Activations