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

    Neuronpedia

    INDEX
    Explanations

    references to different states and their identification in a context related to governance or policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.21
    hey
    -0.17
    luv
    -0.16
    teenth
    -0.15
    them
    -0.15
    meld
    -0.15
    ulk
    -0.15
    aber
    -0.15
    erd
    -0.14
    ne
    -0.14
    POSITIVE LOGITS
    craft
    0.25
    wide
    0.24
    -of
    0.21
    hood
    0.20
     Unidos
    0.19
    ful
    0.19
    /local
    0.19
    -wide
    0.18
    /global
    0.18
    utory
    0.17
    Act Density 0.078%

    No Known Activations