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

    Neuronpedia

    INDEX
    Explanations

    words related to shopping items and products

    oai_token-act-pair · gpt-3.5-turbo

    commas and references to quantities or measurements in a list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izen
    -0.73
    atile
    -0.72
    ,
    -0.69
    otin
    -0.69
    llah
    -0.68
    ,[
    -0.67
     TAMADRA
    -0.66
    ,—
    -0.66
    ":"
    -0.65
    ati
    -0.64
    POSITIVE LOGITS
     huh
    0.97
     please
    0.93
     aka
    0.93
     etc
    0.89
     circa
    0.88
     plus
    0.88
     courtesy
    0.87
     preferably
    0.86
     excluding
    0.85
     including
    0.80
    Act Density 0.328%

    No Known Activations