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

    Neuronpedia

    INDEX
    Explanations

    words related to official positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of systems or categories, specifically ending with 'ary'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ests
    -0.76
    ergy
    -0.69
    ierrez
    -0.69
    ilot
    -0.69
    ortium
    -0.68
    itch
    -0.65
    semb
    -0.64
    essee
    -0.64
    tumblr
    -0.63
     Tanz
    -0.62
    POSITIVE LOGITS
     gland
    0.83
     glands
    0.78
    ksh
    0.74
    clinton
    0.72
     confinement
    0.68
    ussia
    0.63
     GEAR
    0.63
    ature
    0.62
    uments
    0.62
    ansas
    0.61
    Act Density 0.027%

    No Known Activations