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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to motion or activity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NES
    -0.66
    OV
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    é¾įåĸļ士
    -0.63
    ONSORED
    -0.61
    ESA
    -0.60
    IFE
    -0.60
    OB
    -0.59
    ãĤ´
    -0.59
    atform
    -0.59
    POSITIVE LOGITS
     abound
    0.94
     prolifer
    0.78
     populate
    0.71
     converge
    0.68
     clustered
    0.68
     plentiful
    0.65
     circulate
    0.63
    were
    0.62
    hops
    0.61
     roam
    0.61
    Act Density 1.069%

    No Known Activations