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

    Neuronpedia

    INDEX
    Explanations

    references to organizational structures and business entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    POSIT
    -0.16
    sti
    -0.16
    lem
    -0.16
     Hag
    -0.15
    erp
    -0.14
    uti
    -0.14
    -rich
    -0.14
    PEND
    -0.14
    grav
    -0.13
    Pts
    -0.13
    POSITIVE LOGITS
     devoted
    0.25
     dedicated
    0.23
     model
    0.20
    -model
    0.19
     modeled
    0.19
     dedi
    0.18
     Dedicated
    0.18
     dedic
    0.17
     dedicate
    0.17
    ded
    0.17
    Act Density 0.136%

    No Known Activations