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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions among people in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     branch
    -0.15
    urtle
    -0.14
    ambre
    -0.14
    omal
    -0.14
     field
    -0.14
    chor
    -0.14
    ¢åįķ
    -0.14
    osing
    -0.13
    oval
    -0.13
    170
    -0.13
    POSITIVE LOGITS
    çĵľ
    0.17
    umont
    0.16
    ninger
    0.15
     himself
    0.14
    esters
    0.14
    lama
    0.14
    两人
    0.14
    论
    0.14
    ignKey
    0.14
    ernet
    0.14
    Act Density 0.408%

    No Known Activations