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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal rights and trademark infringement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favored
    -0.17
    favor
    -0.17
    behavior
    -0.16
     behaviors
    -0.16
     honored
    -0.15
     labeled
    -0.15
    avior
    -0.15
     behavior
    -0.15
     traveler
    -0.15
     traveled
    -0.14
    POSITIVE LOGITS
     :-↵
    0.24
    -↵
    0.22
     shall
    0.22
    ,-
    0.21
    ,—
    0.21
     connexion
    0.20
     authorised
    0.19
    —↵↵
    0.19
     such
    0.19
     licence
    0.18
    Act Density 0.016%

    No Known Activations