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

    Neuronpedia

    INDEX
    Explanations

    expressions related to familial and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itizen
    -0.15
    lio
    -0.14
    abilit
    -0.14
    okies
    -0.14
    ubic
    -0.14
    лÑıд
    -0.13
     баÑĤÑĮкÑĸв
    -0.13
    ibel
    -0.13
    oretical
    -0.13
    thern
    -0.13
    POSITIVE LOGITS
     ranks
    0.18
    ivery
    0.16
    st
    0.15
     things
    0.15
     Ùħباش
    0.15
     Dud
    0.15
     other
    0.14
     themselves
    0.14
    swick
    0.14
    akan
    0.14
    Act Density 0.058%

    No Known Activations