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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific terms or technical details

    oai_token-act-pair · gpt-3.5-turbo

    specific scientific or technical terms related to materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TW
    -0.73
     NZ
    -0.71
     Jiu
    -0.69
     PB
    -0.69
     Kaw
    -0.68
     Hack
    -0.68
     WW
    -0.68
     Fitz
    -0.67
     Hon
    -0.66
     PAL
    -0.66
    POSITIVE LOGITS
    idation
    1.08
    odes
    1.06
    olic
    1.03
    ansion
    1.03
    opter
    1.03
    atorial
    1.02
    uments
    1.00
    eal
    0.99
    idy
    0.99
    osition
    0.98
    Act Density 0.138%

    No Known Activations