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

    Neuronpedia

    INDEX
    Explanations

    words related to physical activity and fitness

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "get" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palestin
    -0.70
     intest
    -0.66
    Ire
    -0.64
     obser
    -0.64
     defe
    -0.63
     charact
    -0.62
     distingu
    -0.62
     conduc
    -0.62
     departure
    -0.61
     livest
    -0.61
    POSITIVE LOGITS
    TING
    1.26
    tin
    1.24
    ters
    0.96
    ti
    0.92
    tered
    0.90
    rics
    0.87
    ter
    0.87
    rov
    0.86
    emp
    0.86
    tes
    0.86
    Act Density 0.022%

    No Known Activations