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

    Neuronpedia

    INDEX
    Explanations

    words related to enterprising or surprising actions

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "surprise."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hierarch
    -0.73
     corrid
    -0.72
     carbohyd
    -0.71
    odynam
    -0.70
     livest
    -0.70
     structured
    -0.67
     tiss
    -0.67
     steered
    -0.66
     proposed
    -0.65
    ĥ
    -0.65
    POSITIVE LOGITS
    prising
    1.27
    prise
    1.23
    prises
    1.09
    ãĥ¼ãĥĨãĤ£
    1.02
    ãĤ©
    0.99
    DragonMagazine
    0.97
    xtap
    0.93
    ODUCT
    0.83
    ilus
    0.82
    terday
    0.81
    Act Density 0.011%

    No Known Activations