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

    Neuronpedia

    INDEX
    Explanations

    personal reflections on love and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orks
    -0.15
     Zusammen
    -0.13
     Literal
    -0.13
    ä¹ħä¹ħ
    -0.13
    wart
    -0.13
    733
    -0.13
    rieb
    -0.13
    wj
    -0.13
    ìłĿ
    -0.13
    izzle
    -0.13
    POSITIVE LOGITS
     Pis
    0.17
    ufig
    0.15
    avin
    0.15
    isin
    0.14
    akin
    0.14
    μμα
    0.13
    ployment
    0.13
    èĭ
    0.13
     lies
    0.13
     alone
    0.13
    Act Density 0.130%

    No Known Activations