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

    Neuronpedia

    INDEX
    Explanations

    mentions of emotional connections and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thru
    -0.22
     doch
    -0.15
     accordingly
    -0.14
    oir
    -0.14
     пÑĥÑĤем
    -0.14
    ulg
    -0.13
    UTERS
    -0.13
    =explode
    -0.13
    iani
    -0.13
    iliz
    -0.13
    POSITIVE LOGITS
     though
    1.30
    though
    1.06
     Though
    1.05
    Though
    1.01
     tho
    0.71
     however
    0.40
     aunque
    0.40
     allerdings
    0.40
     jedoch
    0.34
     ÏĮμÏīÏĤ
    0.32
    Act Density 0.581%

    No Known Activations