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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or familiarity with popular topics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    filer
    -0.20
    ugged
    -0.16
     Barrel
    -0.15
    lator
    -0.14
    fila
    -0.14
    /cal
    -0.14
    cimal
    -0.14
    .Types
    -0.14
    apolis
    -0.14
    าà¸ĺ
    -0.14
    POSITIVE LOGITS
     fond
    0.17
     yourself
    0.15
    803
    0.15
    аниÑĨ
    0.15
    ATES
    0.14
    asn
    0.14
    ÐĽÐ¬
    0.14
    ÄĽÅ¾
    0.14
    agu
    0.14
     Indo
    0.14
    Act Density 0.081%

    No Known Activations