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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases with the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    references to a central topic or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.78
    hered
    -0.74
    soever
    -0.74
    PLIED
    -0.73
    then
    -0.73
    edia
    -0.72
    lessly
    -0.71
    SPONSORED
    -0.70
    cia
    -0.69
    onse
    -0.68
    POSITIVE LOGITS
     proverbial
    0.96
     fray
    0.96
     bandwagon
    0.90
     joke
    0.88
     fun
    0.87
     deed
    0.86
     groove
    0.84
     popcorn
    0.82
     festivities
    0.80
     madness
    0.79
    Act Density 0.249%

    No Known Activations